|
46279
|
1652
|
33
|
2026-05-15T06:56:41.974072+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828201974_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp> 0.meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comJiminny Tech Day - in 4 mlNikolay Yankov (Presenting)100% <7• Fri 15 May 9:56:4107 8Tab•8• Fii 16 May 9:567 Platto$F15Jiminny MCPget_callLasts cal boptionsoerdealsearch_dealslist_deal_activitieslist_deal_optionsCowKXget_me51 ServiceE3 3nE83 Promol÷ Athenl83 MCP -(a Scher© CursorC ProjectsE Datadog*xIas detected from the audio.account cbjectThe account associated with this call. Nul il not linked to any account.• deal object• lead objectThe lead associated with this call. Nut if not linked to any lead.boan contacsobjectThe main contact associated with this call. Null if not linked to any contact.• category ebject The call type category assigned to this call, e.g. Discovery, Demo, Renewal, Nul il uncategorised.|• stats ebject Call analytics. All fields are null if analytics are unavallable for this organisation's plan or if the call has not been fully• al_score ebject Al scorecard evaluation of the call, Null if no Al scorecard has been run.sumnary string AJ-generated one-paragraph overview of the call - who was involved, what was discussed, and the overall purpose. Fordetalled takeawsys with timestamps, see key_points. Null il not yet generated.* key_points array Al-extracted key points grouped by topic, each anchored to timestamps in the recording. Empty array if not yet |ocherated.• action_itens array: Al-extracted action items identified in the call. Empty array if none identified or not yet processed.* notes array. Manual notes added to this call by team members. Notes may be anchored to a specific timestamp in the recording.• moments arrayNamed segments bookmarked by team members at specific points in the recording. When present, these representin-curated highlights worth noting — e.g. 'Objection Handling", 'Pricing Discussion", "Key Decision'. Empty if nochte tore oeeh marxed• comments arrayTeam collaboration comments on this call in chronological order, flattened from any thread structure. Only commentsvisible to the authenticated user are included.All questions detected in the call with speaker attribution. Typically 20-80 items depending on call length.• themes 'Detected themes and topics aggregated from trigger matches, preserving the three-level hierarchy: theme → topic →trigger phrases. Raw trigger count can be much higher — use include_transcript to locate specific mentions precisely.• transcraot arrayrull spcaker-soparated transchot as short soeech scoments, lyoicaly 200-800 Scoments lor a 30-minute cal =lsignificantly increases response size. Only present when include_transcript is true, null otherwise. Request this onlywhen the user explicitly asks to read the call, needs a specific quote, or when summary, key_points, and topics donot provide sufficient detail.C Dev.Stefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:56 AM | Daily - PlatformLukas Kovalik9:28...
|
NULL
|
6524527273427331009
|
NULL
|
click
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp> 0.meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comJiminny Tech Day - in 4 mlNikolay Yankov (Presenting)100% <7• Fri 15 May 9:56:4107 8Tab•8• Fii 16 May 9:567 Platto$F15Jiminny MCPget_callLasts cal boptionsoerdealsearch_dealslist_deal_activitieslist_deal_optionsCowKXget_me51 ServiceE3 3nE83 Promol÷ Athenl83 MCP -(a Scher© CursorC ProjectsE Datadog*xIas detected from the audio.account cbjectThe account associated with this call. Nul il not linked to any account.• deal object• lead objectThe lead associated with this call. Nut if not linked to any lead.boan contacsobjectThe main contact associated with this call. Null if not linked to any contact.• category ebject The call type category assigned to this call, e.g. Discovery, Demo, Renewal, Nul il uncategorised.|• stats ebject Call analytics. All fields are null if analytics are unavallable for this organisation's plan or if the call has not been fully• al_score ebject Al scorecard evaluation of the call, Null if no Al scorecard has been run.sumnary string AJ-generated one-paragraph overview of the call - who was involved, what was discussed, and the overall purpose. Fordetalled takeawsys with timestamps, see key_points. Null il not yet generated.* key_points array Al-extracted key points grouped by topic, each anchored to timestamps in the recording. Empty array if not yet |ocherated.• action_itens array: Al-extracted action items identified in the call. Empty array if none identified or not yet processed.* notes array. Manual notes added to this call by team members. Notes may be anchored to a specific timestamp in the recording.• moments arrayNamed segments bookmarked by team members at specific points in the recording. When present, these representin-curated highlights worth noting — e.g. 'Objection Handling", 'Pricing Discussion", "Key Decision'. Empty if nochte tore oeeh marxed• comments arrayTeam collaboration comments on this call in chronological order, flattened from any thread structure. Only commentsvisible to the authenticated user are included.All questions detected in the call with speaker attribution. Typically 20-80 items depending on call length.• themes 'Detected themes and topics aggregated from trigger matches, preserving the three-level hierarchy: theme → topic →trigger phrases. Raw trigger count can be much higher — use include_transcript to locate specific mentions precisely.• transcraot arrayrull spcaker-soparated transchot as short soeech scoments, lyoicaly 200-800 Scoments lor a 30-minute cal =lsignificantly increases response size. Only present when include_transcript is true, null otherwise. Request this onlywhen the user explicitly asks to read the call, needs a specific quote, or when summary, key_points, and topics donot provide sufficient detail.C Dev.Stefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:56 AM | Daily - PlatformLukas Kovalik9:28...
|
46277
|
NULL
|
NULL
|
NULL
|
|
46278
|
1653
|
14
|
2026-05-15T06:56:41.962660+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828201962_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLaterMoreFirefoxMistorbookmarksToolsJiminn ActivityLaterMoreFirefoxMistorbookmarksToolsJiminny…..# jiminny-bg# platform-tickets# product launches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...• Direct messages8. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil VasilevA. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham "Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira Cloud® ToastProtllesWindowmelp# releases8 22• Messagesr Filese Bookmarks20881): UpgiToday~ y Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master oy(574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall saresand logginga548fbbe - JY-20908 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerrorShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.5991oel(https://github.com/jiminny/prophet/commit/759976e18aa28d3b66030eebb36d908a92461266- Y-208811(https://jiminny.atlassian.net/browse/JY-Message #releases+ Aa IMlib- scrI scroPlattorm Sprint 4 Q2 - Plattorm TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastic• JY-20903 Update activity stage wJY-20891 add support for second:* (SRD-6853] Moxso - Potential XNew Tab- New TabJlminny.aulasslan.nev/lfa/servicedeskRD/queues/custom/37/SRD-6853O JIMINNY@ For you© Recent# Starred8f Apps0, Spaces+...? Jiminny (New)Q Service-DeskE Queues- ..•Team Priorityf All open tickets 15@ Unassigned t... 5E Support tea...• Raised by me@ Assigned to ...@ Service requ...1E Platform team@ Processing t...Site reliability... O•i New features….. o@ InfoSec issues 0# Ready for Cu... O@ Resolved ti.. 999+= View all queuesE Service requestsA Incidentsbl Reports@ Operations# Knowledge Base0 CustomersChannelsEmail logs< Develoner escalationsSlack integration& Reporting CenterQ Search< BackSE SRD-6853Moxso - Potential deal stages bugi Link work item ?v|¿ Add form+ Escalate work itemD Add designCreate v..GD Gabriela Dureva raised this request via JiraDescriptionHi team,Moxso flaqged that the following conversation was recorded while the deal was still at the Discovery stage:https://app.jiminny.eu/playback/975c6830-7d49-4cle-b2e9-ac80c10a738aShortly after the call ended, the rep updated the deal stage to Closed Lost. The issue is that when the client uses the Stage at Call filter in On Demand and selects Discovery, this recording doesnot aooear.Would we be able to check what the deal stage was at the time the recording took place, and whether there may be a bug causing the recording not to show up under the Stage at Call - Discoveryfilter?Thank vou.Gabbysteps to reproaucenraImpactNoneRoot causeNoneACtIVItVHistorvWork lodAporovals• Summarise 2 comments =Add internal notelReniv to customeiPro tip: press M to comment)Lukas Kovalik 21 hours ago & Internal noteThe activity was matched to another opportunity 253868114162 also called nordhusene.dk1 [2826-84-26 03:14:821 production.INF0: [Calendar] Updated activity cam data ("activity_id": "975C6830-7d49-4c-b2e9-ac88c10a738a", "origina_data"S0 libl @ & Jiminny Tech Day - in 4m A+ Create100% €/2 8• Fri 15 May 9:56:41DAsK RoVoD® @In ProgressDetailsAssignee@ Lukas KovalikReporterG Gabriela DurevaRequest TypeNoneKnowledge base # View related art...Type of Infosec incidentNonePriority level(P2 MediumComponents(InfoSec)NoneComponentsNoneExpected outcomeThe recording shows when the client selectsStage at call - discoveryActual outcomen/aData Centre(EUDev TeamPlatform teamCustomer typeMid MarketSeverity levels2...
|
NULL
|
-817797479616230418
|
NULL
|
click
|
ocr
|
NULL
|
ActivityLaterMoreFirefoxMistorbookmarksToolsJiminn ActivityLaterMoreFirefoxMistorbookmarksToolsJiminny…..# jiminny-bg# platform-tickets# product launches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...• Direct messages8. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil VasilevA. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham "Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira Cloud® ToastProtllesWindowmelp# releases8 22• Messagesr Filese Bookmarks20881): UpgiToday~ y Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master oy(574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall saresand logginga548fbbe - JY-20908 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerrorShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.5991oel(https://github.com/jiminny/prophet/commit/759976e18aa28d3b66030eebb36d908a92461266- Y-208811(https://jiminny.atlassian.net/browse/JY-Message #releases+ Aa IMlib- scrI scroPlattorm Sprint 4 Q2 - Plattorm TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastic• JY-20903 Update activity stage wJY-20891 add support for second:* (SRD-6853] Moxso - Potential XNew Tab- New TabJlminny.aulasslan.nev/lfa/servicedeskRD/queues/custom/37/SRD-6853O JIMINNY@ For you© Recent# Starred8f Apps0, Spaces+...? Jiminny (New)Q Service-DeskE Queues- ..•Team Priorityf All open tickets 15@ Unassigned t... 5E Support tea...• Raised by me@ Assigned to ...@ Service requ...1E Platform team@ Processing t...Site reliability... O•i New features….. o@ InfoSec issues 0# Ready for Cu... O@ Resolved ti.. 999+= View all queuesE Service requestsA Incidentsbl Reports@ Operations# Knowledge Base0 CustomersChannelsEmail logs< Develoner escalationsSlack integration& Reporting CenterQ Search< BackSE SRD-6853Moxso - Potential deal stages bugi Link work item ?v|¿ Add form+ Escalate work itemD Add designCreate v..GD Gabriela Dureva raised this request via JiraDescriptionHi team,Moxso flaqged that the following conversation was recorded while the deal was still at the Discovery stage:https://app.jiminny.eu/playback/975c6830-7d49-4cle-b2e9-ac80c10a738aShortly after the call ended, the rep updated the deal stage to Closed Lost. The issue is that when the client uses the Stage at Call filter in On Demand and selects Discovery, this recording doesnot aooear.Would we be able to check what the deal stage was at the time the recording took place, and whether there may be a bug causing the recording not to show up under the Stage at Call - Discoveryfilter?Thank vou.Gabbysteps to reproaucenraImpactNoneRoot causeNoneACtIVItVHistorvWork lodAporovals• Summarise 2 comments =Add internal notelReniv to customeiPro tip: press M to comment)Lukas Kovalik 21 hours ago & Internal noteThe activity was matched to another opportunity 253868114162 also called nordhusene.dk1 [2826-84-26 03:14:821 production.INF0: [Calendar] Updated activity cam data ("activity_id": "975C6830-7d49-4c-b2e9-ac88c10a738a", "origina_data"S0 libl @ & Jiminny Tech Day - in 4m A+ Create100% €/2 8• Fri 15 May 9:56:41DAsK RoVoD® @In ProgressDetailsAssignee@ Lukas KovalikReporterG Gabriela DurevaRequest TypeNoneKnowledge base # View related art...Type of Infosec incidentNonePriority level(P2 MediumComponents(InfoSec)NoneComponentsNoneExpected outcomeThe recording shows when the client selectsStage at call - discoveryActual outcomen/aData Centre(EUDev TeamPlatform teamCustomer typeMid MarketSeverity levels2...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46274
|
1653
|
12
|
2026-05-15T06:56:35.906756+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828195906_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLateMoreslackVIewJiminny ...# jiminny-bg# ActivityLateMoreslackVIewJiminny ...# jiminny-bg# platform-ticketsc productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya AngelovaVasil Vasilevn Stefka StoyanovaSe: Todor StamatovN Mario GeorgievNikolay Ivanova James Graham *o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.::: Apps" Jira Cloud8 ToastHistoryWindowHelp@ Describe what you are looking for# releases9 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.5991oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa €github.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stac XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumiThe PappLoaicThe seObseonly sonnoicomr(avoicthe coapp,RespaThe cnullsmatclMay 2026 Week20Mon iiX Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00l09:56 Daily - Platform O11:00Tue 121Preparation for 1[Support Daily, 1 Support Daily 15:00Wed 1sSuoport Daily 15:00I| Sprint Review"Jiminny lech Day • In 4 m100% Lz• Fri 15 May 9:56:35Week vTodavFri 15SatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)S -v seceh1 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
8849206878261980844
|
NULL
|
click
|
ocr
|
NULL
|
ActivityLateMoreslackVIewJiminny ...# jiminny-bg# ActivityLateMoreslackVIewJiminny ...# jiminny-bg# platform-ticketsc productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya AngelovaVasil Vasilevn Stefka StoyanovaSe: Todor StamatovN Mario GeorgievNikolay Ivanova James Graham *o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.::: Apps" Jira Cloud8 ToastHistoryWindowHelp@ Describe what you are looking for# releases9 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.5991oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa €github.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stac XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumiThe PappLoaicThe seObseonly sonnoicomr(avoicthe coapp,RespaThe cnullsmatclMay 2026 Week20Mon iiX Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00l09:56 Daily - Platform O11:00Tue 121Preparation for 1[Support Daily, 1 Support Daily 15:00Wed 1sSuoport Daily 15:00I| Sprint Review"Jiminny lech Day • In 4 m100% Lz• Fri 15 May 9:56:35Week vTodavFri 15SatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)S -v seceh1 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46247
|
1653
|
4
|
2026-05-15T06:54:35.787411+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828075787_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLateMoreNotion CalendarVIewJiminny ...# ji ActivityLateMoreNotion CalendarVIewJiminny ...# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya Angelova• Vasil VasilevN Stefka StovanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.#: Apps" Jira Cloud8 ToastWindowmelt@ Describe what you are looking for# releases8 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.599oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa Igithub.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stag XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumThe PFixAappLoaicMav 2026 Week20Mon iiTue 12X Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00lThe seObseonly sComr(avoicthe cano.RespThe cnulismatcl09:54 Daily -Platform11:001Preparation for 1[Support Daily, 1 Support Daily 15:0020:00Wed1son 12Suoport Daily 15:00I| Sprint ReviewDally - Platrorm • now100% Lz• Fri 15 May 9:54:35Week vTodavSatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)Fri 151 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
5840374313275624374
|
NULL
|
click
|
ocr
|
NULL
|
ActivityLateMoreNotion CalendarVIewJiminny ...# ji ActivityLateMoreNotion CalendarVIewJiminny ...# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya Angelova• Vasil VasilevN Stefka StovanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.#: Apps" Jira Cloud8 ToastWindowmelt@ Describe what you are looking for# releases8 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.599oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa Igithub.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stag XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumThe PFixAappLoaicMav 2026 Week20Mon iiTue 12X Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00lThe seObseonly sComr(avoicthe cano.RespThe cnulismatcl09:54 Daily -Platform11:001Preparation for 1[Support Daily, 1 Support Daily 15:0020:00Wed1son 12Suoport Daily 15:00I| Sprint ReviewDally - Platrorm • now100% Lz• Fri 15 May 9:54:35Week vTodavSatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)Fri 151 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46246
|
1652
|
11
|
2026-05-15T06:54:30.047379+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828070047_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% <2• Fri 15 May 9:54:29Nikolay Yankov (Presenting)0n 87 PlattoJiminny MCPget_call**List_call_optionsget_dealsearch_dealslist_deal_activitieslist_deal_optionsCowKX15get_me57 ServiceE3 383 Promel( Ament x | E3 MCP- x [) Scher x C Cursor X | * Claude x*0ЯG0• CoRIC XCMOP KIC Projectse croke!e Sely XL Taske9 tools• id istring Internal UUID for this deal.• name istring Dealname, e.g. 'Acme Corp - Renewal (31/05/2026). |cre_url string. Direct link to this deal in the connected CRM.• crm_name Istring Name of the connected CRM, e.g. 'Salesforce", "HubSpot'!.• owner cbject The rep who owns this deal.• account ebject. The account this desl belongs to. Null il not linked.• value ebject Monetary value of the deal. Null it no value has been set.• open_date string When the deal was created. ISO 8601.•close_date string Expected or actual close date. ISO 8601 (YYYY-MM-DD).• 15_closed Bootean True il the deal has been closed (won or lost).•is_won boolean True if the deal was won. Only meaningtul when is_closed is true. To find lost deals, check is_closed: true and is_wondfaise.• current_stage ebject The pipeline stage this deal is currently in. Null if no stage is set.• stage_history array Chronological list of stage transitions this deal has gone through, oldest first. Useful for understanding dealprogression and velocity. Only includes stages actually visited, not all possible pipeline stages.• risks arrayActive deal risks detected for this deal. Each entry is a plain-English description of a specific risk signal, e.g. "No responselor 3 weeks, Close date nas passed. tmpty artay i no active fisks)• activity_countsSummary count of all communications linked to this deal by type. Use list_dealLactivities to see the actual• contacts arrayexcoaeocukeewnitnlhceetmovatvtno coneemiuean• crn_field_values arrayCRM field values configured for this deal by the organisation, e.g. forecast category, probability justification,opportunity risks, next steps. Fields that duplicate top-level data (value, close_date, current_stage) arecustom fields have been configured.- Dev8• Fri 15 May 9:54L Al BockmarxsNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform• 7:15...
|
NULL
|
254968608003940863
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% <2• Fri 15 May 9:54:29Nikolay Yankov (Presenting)0n 87 PlattoJiminny MCPget_call**List_call_optionsget_dealsearch_dealslist_deal_activitieslist_deal_optionsCowKX15get_me57 ServiceE3 383 Promel( Ament x | E3 MCP- x [) Scher x C Cursor X | * Claude x*0ЯG0• CoRIC XCMOP KIC Projectse croke!e Sely XL Taske9 tools• id istring Internal UUID for this deal.• name istring Dealname, e.g. 'Acme Corp - Renewal (31/05/2026). |cre_url string. Direct link to this deal in the connected CRM.• crm_name Istring Name of the connected CRM, e.g. 'Salesforce", "HubSpot'!.• owner cbject The rep who owns this deal.• account ebject. The account this desl belongs to. Null il not linked.• value ebject Monetary value of the deal. Null it no value has been set.• open_date string When the deal was created. ISO 8601.•close_date string Expected or actual close date. ISO 8601 (YYYY-MM-DD).• 15_closed Bootean True il the deal has been closed (won or lost).•is_won boolean True if the deal was won. Only meaningtul when is_closed is true. To find lost deals, check is_closed: true and is_wondfaise.• current_stage ebject The pipeline stage this deal is currently in. Null if no stage is set.• stage_history array Chronological list of stage transitions this deal has gone through, oldest first. Useful for understanding dealprogression and velocity. Only includes stages actually visited, not all possible pipeline stages.• risks arrayActive deal risks detected for this deal. Each entry is a plain-English description of a specific risk signal, e.g. "No responselor 3 weeks, Close date nas passed. tmpty artay i no active fisks)• activity_countsSummary count of all communications linked to this deal by type. Use list_dealLactivities to see the actual• contacts arrayexcoaeocukeewnitnlhceetmovatvtno coneemiuean• crn_field_values arrayCRM field values configured for this deal by the organisation, e.g. forecast category, probability justification,opportunity risks, next steps. Fields that duplicate top-level data (value, close_date, current_stage) arecustom fields have been configured.- Dev8• Fri 15 May 9:54L Al BockmarxsNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform• 7:15...
|
46245
|
NULL
|
NULL
|
NULL
|
|
46245
|
1652
|
10
|
2026-05-15T06:54:27.027704+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828067027_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlDaily - Platform - now100% 123 • Fri 15 May 9:54:26meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)07 87 Placto$**F15Jiminny MCPget_callList_call_optionsget_dealsearch_dealslist_deal_activitieslist_deal_optionsCowKXget_me57 ServiceE83 PromelAcert x* McP•X Scher X0 Curso X * Claude XC Projects|ecrоkeaserky X L taseGet full details of a single deal by ID. Returns: deal name, owner, account, value, open and close dates, current stage with entry time,full stage history, active deal risks as plain-English descriptions, CRM contacts linked to the deal, CRM field values configured by theorganisation, and activity counts by type. For the actual list of calls and emails linked to this deal, call list_deal_activities.INPUTSidrequiredThe UUID of the deal.OUTPUT FIELDS•id string Internal UUID for this deal.•name istring Dealname, e.g. 'Acme Corp - Renewal (31/05/2026).• cre_url string Direct link to this deal in the connected CRM• Cra_name string Name of the connected CRM, e.g. 'Salesforce', "HubSpot'.• owner |The rep who owns this deal.• account cbject The account this deal belongs to. Nul it not linked.* value ebject Monetary value of the deal. Null il no value has been set.open_date [string. When the desl was created. ISO 8601.• close_date string Expected or actual close date. ISO 8601 (YYYY-MM-DD).|•Is_closed Boolean True if the deal has been closed (won or lost).• is_won boolean True if the deal was won. Only meaningful when is_closed is true. To find lost deals, check is_closed: true and is_won:lene• current_stagecbject The pipeline stage this deal is currently in. Null if no stage is set.• stage_history |arrayCnronological list or stage transzoons this deai nas gone througn, cloest rrst. Userul for understanding dealprogression and velocity. Only includes stages actually visited, not all possible pipeline stages.|• risks |Active deal risks detected for this deal. Each entry is a plain-English description of a specific risk signal, e.g. 'No responsefor 3 weeks', 'Close date has passed". Empty array if no active risks.0ЯG0MOPT125%8• Fri 15 May 9:54L Al BookmarxsNikolay IvanovGalya Dimitrova3 othersNikolay Yankov9:54 AM | Daily - PlatformLukas Kovalik• 7:12...
|
NULL
|
-6939000331477417552
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlDaily - Platform - now100% 123 • Fri 15 May 9:54:26meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)07 87 Placto$**F15Jiminny MCPget_callList_call_optionsget_dealsearch_dealslist_deal_activitieslist_deal_optionsCowKXget_me57 ServiceE83 PromelAcert x* McP•X Scher X0 Curso X * Claude XC Projects|ecrоkeaserky X L taseGet full details of a single deal by ID. Returns: deal name, owner, account, value, open and close dates, current stage with entry time,full stage history, active deal risks as plain-English descriptions, CRM contacts linked to the deal, CRM field values configured by theorganisation, and activity counts by type. For the actual list of calls and emails linked to this deal, call list_deal_activities.INPUTSidrequiredThe UUID of the deal.OUTPUT FIELDS•id string Internal UUID for this deal.•name istring Dealname, e.g. 'Acme Corp - Renewal (31/05/2026).• cre_url string Direct link to this deal in the connected CRM• Cra_name string Name of the connected CRM, e.g. 'Salesforce', "HubSpot'.• owner |The rep who owns this deal.• account cbject The account this deal belongs to. Nul it not linked.* value ebject Monetary value of the deal. Null il no value has been set.open_date [string. When the desl was created. ISO 8601.• close_date string Expected or actual close date. ISO 8601 (YYYY-MM-DD).|•Is_closed Boolean True if the deal has been closed (won or lost).• is_won boolean True if the deal was won. Only meaningful when is_closed is true. To find lost deals, check is_closed: true and is_won:lene• current_stagecbject The pipeline stage this deal is currently in. Null if no stage is set.• stage_history |arrayCnronological list or stage transzoons this deai nas gone througn, cloest rrst. Userul for understanding dealprogression and velocity. Only includes stages actually visited, not all possible pipeline stages.|• risks |Active deal risks detected for this deal. Each entry is a plain-English description of a specific risk signal, e.g. 'No responsefor 3 weeks', 'Close date has passed". Empty array if no active risks.0ЯG0MOPT125%8• Fri 15 May 9:54L Al BookmarxsNikolay IvanovGalya Dimitrova3 othersNikolay Yankov9:54 AM | Daily - PlatformLukas Kovalik• 7:12...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46244
|
1652
|
9
|
2026-05-15T06:54:23.975816+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828063975_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp$0.(ah]Daily - Platform - nowmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com100% <2• Fri 15 May 9:54:23Nikolay Yankov (Presenting)07 87 Platto57 Service* Prome( Aent x | E3 MCP- x () Scher x C Cursor x | * Claude x*09G0• CoRIC X | C MCPK XoumineSmin•08 NEDt O@ Cuuse OCrcka LSeny &xL TaskeInsights & CoachinD De LUX8• Fri 15 May 9:54L Al BookmarxsJiminny MCPget_callLts.call_optionsDEALSsearch_dealslist_deal_activitiesList deat optionsseerchteroetget_ne15get_dealGet full details of a single deal by ID, Returns: deal name, owner, account, value, open and close dates, current stage with entrytime, full stage history, active deal risks as plain-English descriptions, CRM contacts inked to the desi, CRM field values configuredby the organisation, and activity counts by type. For the actual list of calls and emails linked to this deal, call ist._dealLactivities.IMPUTSThe UUID of the deal.• id Jstring Internal UUID for this deak.|• hale string ceaname, eg. Aome Corp - Kenema: (3905/2026):,cra_nate atrimg: Name of the corcected CRM, e.g. Salestorce, Mubfoot.oeneUhelee ano 0w7s 20s o6al• eccount eoleet the accovnt bos oea beronos to. Pes lr hot tearo)• Yalve cieetVoneltwededeuno youe honohenseope-oateutri moo becen eas ortaco. lou o0ulelose_date Atring Expected or actual close date. IS0 8601 (MMY-MM-00)• is_von beeleas True if the deal was won. Obly meaningful when is_closed is true. To fied lost deals, check is_closed: true and isJoCuesthot wiectThe soelhe toeetyndesncurterynuno toee?se" Stopenaston arreroweot Ohieuoeshoeweteoontdie oioenesues*risks array Active deal raks detected for this deai. Each entry is a plain-Engiish descriotion of a specitic risk sional, e.g. 'No resel• actávity_cousts wbject• cra_field_valuestner teo weues conegaree loe tns deety te cryNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform7:09...
|
NULL
|
-3677713590894122643
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp$0.(ah]Daily - Platform - nowmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com100% <2• Fri 15 May 9:54:23Nikolay Yankov (Presenting)07 87 Platto57 Service* Prome( Aent x | E3 MCP- x () Scher x C Cursor x | * Claude x*09G0• CoRIC X | C MCPK XoumineSmin•08 NEDt O@ Cuuse OCrcka LSeny &xL TaskeInsights & CoachinD De LUX8• Fri 15 May 9:54L Al BookmarxsJiminny MCPget_callLts.call_optionsDEALSsearch_dealslist_deal_activitiesList deat optionsseerchteroetget_ne15get_dealGet full details of a single deal by ID, Returns: deal name, owner, account, value, open and close dates, current stage with entrytime, full stage history, active deal risks as plain-English descriptions, CRM contacts inked to the desi, CRM field values configuredby the organisation, and activity counts by type. For the actual list of calls and emails linked to this deal, call ist._dealLactivities.IMPUTSThe UUID of the deal.• id Jstring Internal UUID for this deak.|• hale string ceaname, eg. Aome Corp - Kenema: (3905/2026):,cra_nate atrimg: Name of the corcected CRM, e.g. Salestorce, Mubfoot.oeneUhelee ano 0w7s 20s o6al• eccount eoleet the accovnt bos oea beronos to. Pes lr hot tearo)• Yalve cieetVoneltwededeuno youe honohenseope-oateutri moo becen eas ortaco. lou o0ulelose_date Atring Expected or actual close date. IS0 8601 (MMY-MM-00)• is_von beeleas True if the deal was won. Obly meaningful when is_closed is true. To fied lost deals, check is_closed: true and isJoCuesthot wiectThe soelhe toeetyndesncurterynuno toee?se" Stopenaston arreroweot Ohieuoeshoeweteoontdie oioenesues*risks array Active deal raks detected for this deai. Each entry is a plain-Engiish descriotion of a specitic risk sional, e.g. 'No resel• actávity_cousts wbject• cra_field_valuestner teo weues conegaree loe tns deety te cryNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform7:09...
|
46243
|
NULL
|
NULL
|
NULL
|
|
46243
|
1652
|
8
|
2026-05-15T06:54:20.972978+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828060972_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% 12• Fri 15 May 9:54:20Nikolay Yankov (Presenting)07 8M InboxJiminny MCPVALLEget_callLts.call_optionsDEALSsearch_dealslist_deal_activitiesList deal optionsCONTEAseerchreroetget_ne15Tab7 Placto57 ServiceE83 PromelAcert xx Mop• X Schem Xo Curso X * Claude XI*09G0• CRI X | С MOPT:N[URL_WITH_CREDENTIALS] the organisation, and activity counts by type. For the actual list of calls and emalls linked to this deal, call fst._deal_activiies.IAPUTSThe UUID of the deal.• 1d Jatring Internal UUO for this deal.• nate string Deainame, e.@. Acme Corp - Renemal (31/06/2026) -srezureo Сreot 1085 0088шe Сoesi Сucra_nane istring Name of the cornected CRM, e g. 'Salesforce', HubSoor:088VV100 888108 0000078 098 C08 0er0t7 10% neiee l7thot Craco)valueeMontay mwoccooea, huid no vauerot oeen venoproote soimneoeohasdetwwol•Close date string Expected or actuai ciose date. 1SO 6601 (YYYY-MM-CO).43. С803800018 140030000183000800%00 (900 0 1031• is_von [boolean True it the deal was won. Only meaningful when it_closed is true. To find lost dealt, check is_closed: true and iumol• corrent_stage ebject The pipelice stage this deal lis currecty in. Nuß il no stage is vet.• Sadehstonyereryyca st er stage vanstons oes dea nas gone brovgn, eoest trst. osero le vnderstano oe• räsks arrayActive deal riaks detected for this deal. Each entry is a plain-Engish descriction of a specifie risk signal, e.g. '"No respolroroneats, Mortouets bosios cmoty erey cno doure taxa• activity_counts ebjectary court of all communications linked to this deal by type. Use liat, deL acthities to see the achol• contects array CRM contacts assocated with this deal. Emoty array & no contacts ane lnkec)•crontaete vatues arrer8• Fri 15 May 9:54SmirL Al BookmarxsNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform7:06...
|
NULL
|
-3772459803797718530
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% 12• Fri 15 May 9:54:20Nikolay Yankov (Presenting)07 8M InboxJiminny MCPVALLEget_callLts.call_optionsDEALSsearch_dealslist_deal_activitiesList deal optionsCONTEAseerchreroetget_ne15Tab7 Placto57 ServiceE83 PromelAcert xx Mop• X Schem Xo Curso X * Claude XI*09G0• CRI X | С MOPT:N[URL_WITH_CREDENTIALS] the organisation, and activity counts by type. For the actual list of calls and emalls linked to this deal, call fst._deal_activiies.IAPUTSThe UUID of the deal.• 1d Jatring Internal UUO for this deal.• nate string Deainame, e.@. Acme Corp - Renemal (31/06/2026) -srezureo Сreot 1085 0088шe Сoesi Сucra_nane istring Name of the cornected CRM, e g. 'Salesforce', HubSoor:088VV100 888108 0000078 098 C08 0er0t7 10% neiee l7thot Craco)valueeMontay mwoccooea, huid no vauerot oeen venoproote soimneoeohasdetwwol•Close date string Expected or actuai ciose date. 1SO 6601 (YYYY-MM-CO).43. С803800018 140030000183000800%00 (900 0 1031• is_von [boolean True it the deal was won. Only meaningful when it_closed is true. To find lost dealt, check is_closed: true and iumol• corrent_stage ebject The pipelice stage this deal lis currecty in. Nuß il no stage is vet.• Sadehstonyereryyca st er stage vanstons oes dea nas gone brovgn, eoest trst. osero le vnderstano oe• räsks arrayActive deal riaks detected for this deal. Each entry is a plain-Engish descriction of a specifie risk signal, e.g. '"No respolroroneats, Mortouets bosios cmoty erey cno doure taxa• activity_counts ebjectary court of all communications linked to this deal by type. Use liat, deL acthities to see the achol• contects array CRM contacts assocated with this deal. Emoty array & no contacts ane lnkec)•crontaete vatues arrer8• Fri 15 May 9:54SmirL Al BookmarxsNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform7:06...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46242
|
1652
|
7
|
2026-05-15T06:54:17.959286+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828057959_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]Daily - Platform - nowmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com100% L23 • Fri 15 May 9:54:17Nikolay Yankov (Presenting)07 8Jiminny MCPget_callLts.call_optionsDEALSpet_dealsearch_dealslist_deal_activitieslist deal optioasCONTEXseerchreroetget_ne15Plache51 ServiceE3 JminE3 PromelAttentxx MoP• X Schem X o Cursor X * Claude XTe:/l/Users/nikolayyankov/jminny/app/docs/mcp/explorer/explorer.htmlC Projects|ecrceele Serty Xget_dealGet full details of a single deal by 1D, Returns: deal name, owner, account, value, open and close dates, current stage with entrytime, fuli stage history, active deal risks as plain-ngish descriotions, CRM contacts inked to the deal, CRM field values contiouredby the organisation, and activity counts by type. For the actual list of calls and emalls linked to this deal, call ist_deal _activities.Uhewoeee thie oeal•1d string) Internal UUID for this dea)• law sridedNneeAecorpekinnstwedocra_url istrisg: Direct ink to this deal in the connected CRM.• Crn_nate string Name of the connecied CKM, e.g. Salesforce, Hubspot• ouner ebject The reo who ouns this deal• account ebject. The account this deal belongs to. Nufl if not linked.vetve cet montlory mino cue ooot muiu no vãuc hoo bcca kemopc-sootetrim.c0e0008n000co. 130 0001•Close_date atring Expecied or achuai ciose date. 150 6601 (Y77Y-MM-CO)is_closed beslean Trueif the deal has been closed (won or lost)• 1s_von beeleas True i& the deal was won. Only meaningful when is,closed is trve. To find lost deals, check is,closed: true and is,yor• Curreht Stage ebject The poeine stape this deal is currency n. Nul i no stape is selstepeanastonarernoe te e cay ueryaioa ti oel het ane re e diee tent peoe fe easerlinsing cod"citktwenr• activity_counts ebject• contacts array CRM contacts associated with this deal. Empty array it no contacts are linked• cra_field_values array. CRM feld values configured for this deal by the orgaration, e.g. forecast category, probabaty Mtfication.*09G0• CORIC X |CMOP KIL tasknsignts & Coachn.- De bUXQ8• Fri 15 May 9:54SmiriL Al BookmarksNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform7:03...
|
NULL
|
-1776234364187261019
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]Daily - Platform - nowmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com100% L23 • Fri 15 May 9:54:17Nikolay Yankov (Presenting)07 8Jiminny MCPget_callLts.call_optionsDEALSpet_dealsearch_dealslist_deal_activitieslist deal optioasCONTEXseerchreroetget_ne15Plache51 ServiceE3 JminE3 PromelAttentxx MoP• X Schem X o Cursor X * Claude XTe:/l/Users/nikolayyankov/jminny/app/docs/mcp/explorer/explorer.htmlC Projects|ecrceele Serty Xget_dealGet full details of a single deal by 1D, Returns: deal name, owner, account, value, open and close dates, current stage with entrytime, fuli stage history, active deal risks as plain-ngish descriotions, CRM contacts inked to the deal, CRM field values contiouredby the organisation, and activity counts by type. For the actual list of calls and emalls linked to this deal, call ist_deal _activities.Uhewoeee thie oeal•1d string) Internal UUID for this dea)• law sridedNneeAecorpekinnstwedocra_url istrisg: Direct ink to this deal in the connected CRM.• Crn_nate string Name of the connecied CKM, e.g. Salesforce, Hubspot• ouner ebject The reo who ouns this deal• account ebject. The account this deal belongs to. Nufl if not linked.vetve cet montlory mino cue ooot muiu no vãuc hoo bcca kemopc-sootetrim.c0e0008n000co. 130 0001•Close_date atring Expecied or achuai ciose date. 150 6601 (Y77Y-MM-CO)is_closed beslean Trueif the deal has been closed (won or lost)• 1s_von beeleas True i& the deal was won. Only meaningful when is,closed is trve. To find lost deals, check is,closed: true and is,yor• Curreht Stage ebject The poeine stape this deal is currency n. Nul i no stape is selstepeanastonarernoe te e cay ueryaioa ti oel het ane re e diee tent peoe fe easerlinsing cod"citktwenr• activity_counts ebject• contacts array CRM contacts associated with this deal. Empty array it no contacts are linked• cra_field_values array. CRM feld values configured for this deal by the orgaration, e.g. forecast category, probabaty Mtfication.*09G0• CORIC X |CMOP KIL tasknsignts & Coachn.- De bUXQ8• Fri 15 May 9:54SmiriL Al BookmarksNikolay IvanovGalya Dimitrova3 othersNikolay YankovLukas Kovalik9:54 AM | Daily - Platform7:03...
|
46241
|
NULL
|
NULL
|
NULL
|
|
46241
|
1652
|
6
|
2026-05-15T06:54:14.944092+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828054944_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - nowNikolay Yankov (Presenting)100% 12• • Fri 15 May 9:54:1407 8+2 Plarto51 ServiceE3 Promel*Acert xx McP- X Scher X0 Cursor X* Claude X• CORIC X0ЯG0CMOP KDatadog ©A selly XL taskDe bUx8• Fri 15 May 9:54L Al Bookmarks•SJiminny MCPCALLSget_caltLltt.all_optloesDEALget_dealsearch_dealslist_deal_activitieslist deal optionssearch_nenbersget_nelist_deal_activitiesBY DEAL 1OGet all communications linked to a specific deal across all channel types: voice calls, video meetings, emails, and SMS. Returns a |unitied chronological timeline. Each ibem includes type, date, participants or senderirecioient, and titie or subject. Voice and videclitens include an id you can pass to get,.call for full details including transcript, summary, and insights.INPUTStypeOptionally filter ty activity type. Omit to return all types.OUTPUT FIELDSNikolay IvanovGalya Dimitrova3 othersNikolay Yankov•15Lukas Kovalik9:54 AM | Daily - Platform7:00Lộ3...
|
NULL
|
5582282554008185785
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ah]meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - nowNikolay Yankov (Presenting)100% 12• • Fri 15 May 9:54:1407 8+2 Plarto51 ServiceE3 Promel*Acert xx McP- X Scher X0 Cursor X* Claude X• CORIC X0ЯG0CMOP KDatadog ©A selly XL taskDe bUx8• Fri 15 May 9:54L Al Bookmarks•SJiminny MCPCALLSget_caltLltt.all_optloesDEALget_dealsearch_dealslist_deal_activitieslist deal optionssearch_nenbersget_nelist_deal_activitiesBY DEAL 1OGet all communications linked to a specific deal across all channel types: voice calls, video meetings, emails, and SMS. Returns a |unitied chronological timeline. Each ibem includes type, date, participants or senderirecioient, and titie or subject. Voice and videclitens include an id you can pass to get,.call for full details including transcript, summary, and insights.INPUTStypeOptionally filter ty activity type. Omit to return all types.OUTPUT FIELDSNikolay IvanovGalya Dimitrova3 othersNikolay Yankov•15Lukas Kovalik9:54 AM | Daily - Platform7:00Lộ3...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46240
|
1653
|
3
|
2026-05-15T06:54:12.189527+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828052189_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLateMoreNotion CalendarVIewJiminny ...# ji ActivityLateMoreNotion CalendarVIewJiminny ...# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya Angelova• Vasil VasilevN Stefka StovanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.#: Apps" Jira Cloud8 ToastWindowmelt@ Describe what you are looking for# releases8 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.599oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa Igithub.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stag XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumThe PFixAappLoaicMav 2026 Week20Mon iiTue 12X Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00lThe seObseonly sComr(avoicthe cano.RespThe cnulismatcl09:54 Daily -Platform11:001Preparation for 1[Support Daily, 1 Support Daily 15:00Wed1son 12Suoport Daily 15:00I| Sprint ReviewDally - Platrorm • now100% Lz• Fri 15 May 9:54:11Week vTodavSatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)Fri 151 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
6571791006245769129
|
NULL
|
idle
|
ocr
|
NULL
|
ActivityLateMoreNotion CalendarVIewJiminny ...# ji ActivityLateMoreNotion CalendarVIewJiminny ...# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya Angelova• Vasil VasilevN Stefka StovanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.#: Apps" Jira Cloud8 ToastWindowmelt@ Describe what you are looking for# releases8 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.599oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa Igithub.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stag XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumThe PFixAappLoaicMav 2026 Week20Mon iiTue 12X Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00lThe seObseonly sComr(avoicthe cano.RespThe cnulismatcl09:54 Daily -Platform11:001Preparation for 1[Support Daily, 1 Support Daily 15:00Wed1son 12Suoport Daily 15:00I| Sprint ReviewDally - Platrorm • now100% Lz• Fri 15 May 9:54:11Week vTodavSatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)Fri 151 Suoport Dailv 15:001Suoport Daily 16...
|
46236
|
NULL
|
NULL
|
NULL
|
|
46239
|
1652
|
5
|
2026-05-15T06:53:59.818992+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828039818_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)51 ServiceE3 1nE83 PromolAtentx MoP-X Scher XoC[URL_WITH_CREDENTIALS] Improve Story~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commit11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateNoneDaily - Platform - now100% L2Fri 15 May 9:53:59=07 88• Fri 15 May 9:53SmiriGroup: QueriesOEPLOYDeROT(Deadiine 25 May) MigrateDenora moooWepoTCeД л-2081010 =Setup test coverage forProphet in SonarMAINTENANCEDeployedЕ-л-1051110=[Deadiine 17 June] Migratedepricated Gemini modelsDeployed0=1Nikolay IivanovGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:45...
|
NULL
|
-7160429247287822614
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)51 ServiceE3 1nE83 PromolAtentx MoP-X Scher XoC[URL_WITH_CREDENTIALS] Improve Story~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commit11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateNoneDaily - Platform - now100% L2Fri 15 May 9:53:59=07 88• Fri 15 May 9:53SmiriGroup: QueriesOEPLOYDeROT(Deadiine 25 May) MigrateDenora moooWepoTCeД л-2081010 =Setup test coverage forProphet in SonarMAINTENANCEDeployedЕ-л-1051110=[Deadiine 17 June] Migratedepricated Gemini modelsDeployed0=1Nikolay IivanovGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:45...
|
46238
|
NULL
|
NULL
|
NULL
|
|
46238
|
1652
|
4
|
2026-05-15T06:53:56.812114+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828036812_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfiles(ahlDai FirefoxFileEditViewHistoryBookmarksProfiles(ahlDaily - Platform - now100% L2Fri 15 May 9:53:56ToolsWindowHelpmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com07 8Nikolay Yankov (Presenting)51 ServicE3 PromoAttent* MСP -X Scher Xo) CursoX& Claude XIMOPThttps://fiminny.atlassian.net/jra/software/c/projects/JY/boards/37?selectedissue=JY-20835C Projects|15554E DatadogPlatform Team %.Q Search board800$ SY-20739 / A JY-20835Ready To Be Merged 12 work tems)MCP > Enable users to get a list of deals and their detailsO AUTFOK ОУv Sprint. (16 work itema)RLADYOR DEV 5Panorama prompts isCMOODUDUROWAAU RIPORTBacklogД Jy-200763 ...=Notify the user if a SS isdeleted but is used in AJBacklog[ JY-20615~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Result: No deaisfound matching your eriteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fields whichare swored in vimininy por ut and for chow taung), acunibes (oaes, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibllity settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account. Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Upgrade BE Ibraries - MayMAINTENANEISbackоgJy-19958Note: here you can find example prompts for testing - €) Prompts and Skiits~ Subtasks0% DoneAlow ownerooSeiccted When Seton uoatrialPrlorityStor..*xIIn DevI Improve StoryDetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commit11 Create pull request |componentPlatformSub-ProductAdd optionsLabeisNockStory point estimateC Dev8• Fri 15 May 9:53L Al BookmarxsNikolay IvanovGalya DimitrovaDEPLOY 2[Deadiine 25 May) MigrateД л-говв0Setup test coverage forProphet in SonarMAINTENANCEDeployndВ л-1901(Deadine 17 June) Migratedepricated Gemini models0 =13 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:42...
|
NULL
|
7568640190714978220
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfiles(ahlDai FirefoxFileEditViewHistoryBookmarksProfiles(ahlDaily - Platform - now100% L2Fri 15 May 9:53:56ToolsWindowHelpmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com07 8Nikolay Yankov (Presenting)51 ServicE3 PromoAttent* MСP -X Scher Xo) CursoX& Claude XIMOPThttps://fiminny.atlassian.net/jra/software/c/projects/JY/boards/37?selectedissue=JY-20835C Projects|15554E DatadogPlatform Team %.Q Search board800$ SY-20739 / A JY-20835Ready To Be Merged 12 work tems)MCP > Enable users to get a list of deals and their detailsO AUTFOK ОУv Sprint. (16 work itema)RLADYOR DEV 5Panorama prompts isCMOODUDUROWAAU RIPORTBacklogД Jy-200763 ...=Notify the user if a SS isdeleted but is used in AJBacklog[ JY-20615~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Result: No deaisfound matching your eriteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fields whichare swored in vimininy por ut and for chow taung), acunibes (oaes, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibllity settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account. Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Upgrade BE Ibraries - MayMAINTENANEISbackоgJy-19958Note: here you can find example prompts for testing - €) Prompts and Skiits~ Subtasks0% DoneAlow ownerooSeiccted When Seton uoatrialPrlorityStor..*xIIn DevI Improve StoryDetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commit11 Create pull request |componentPlatformSub-ProductAdd optionsLabeisNockStory point estimateC Dev8• Fri 15 May 9:53L Al BookmarxsNikolay IvanovGalya DimitrovaDEPLOY 2[Deadiine 25 May) MigrateД л-говв0Setup test coverage forProphet in SonarMAINTENANCEDeployndВ л-1901(Deadine 17 June) Migratedepricated Gemini models0 =13 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:42...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46237
|
1652
|
3
|
2026-05-15T06:53:41.669379+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828021669_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)Daily - Platform - now100% 12• Fri 15 May 9:53:41=07 88• Fri 15 May 9:53$57 ServiceE3 3mlE83 PromelAthent* MoP-XK Scher xo Curso X * Claude Xhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835C Projects|Datadog* CaudPlatform Team %.Q Search board$ SY-20739 / A JY-20835Ready To Be Merged (2 work tems)KAUTYOKUVv Sprint (16 work items)RLADY OR DEV 5Panorama prompts isCwOOUDUOUAAU RiPORTBacklogД JY-200763 -.=0Notify the user it a SS isdeleted but is used in AJReportAКVOKTBacklogWtowotUpgrade BE Ibraries - MayMAINTENANEISbackiоg@ JY-19958AixwownerSeiected When Sctone LoatrialMCP > Enable users to get a list of deals and their details~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Resuft: No dealsfound matching your criteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fieids whichare stored in vimininy por bt and for chow talng), acunioes (cars, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibillty settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Note: here you can find example prompts for testing - E) Prompts and SkiltsSubtasks..•_ -0% DonePriorityStor...ASSRARIn Dev v~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commt11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateС МОР ТC DevI Improve StorySminiGroup: QueriesDEPLOY 2BERLOT(Deadiine 25 May) Migrateemr moooД л-2088010 =Setup test coverage forProphet in SonarDeployedЕ л-151110=(Deadiine 17 June) Migratedepricated Gemini models©3-20272Stefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:27...
|
NULL
|
15619001990883674
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)Daily - Platform - now100% 12• Fri 15 May 9:53:41=07 88• Fri 15 May 9:53$57 ServiceE3 3mlE83 PromelAthent* MoP-XK Scher xo Curso X * Claude Xhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835C Projects|Datadog* CaudPlatform Team %.Q Search board$ SY-20739 / A JY-20835Ready To Be Merged (2 work tems)KAUTYOKUVv Sprint (16 work items)RLADY OR DEV 5Panorama prompts isCwOOUDUOUAAU RiPORTBacklogД JY-200763 -.=0Notify the user it a SS isdeleted but is used in AJReportAКVOKTBacklogWtowotUpgrade BE Ibraries - MayMAINTENANEISbackiоg@ JY-19958AixwownerSeiected When Sctone LoatrialMCP > Enable users to get a list of deals and their details~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Resuft: No dealsfound matching your criteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fieids whichare stored in vimininy por bt and for chow talng), acunioes (cars, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibillty settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Note: here you can find example prompts for testing - E) Prompts and SkiltsSubtasks..•_ -0% DonePriorityStor...ASSRARIn Dev v~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commt11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateС МОР ТC DevI Improve StorySminiGroup: QueriesDEPLOY 2BERLOT(Deadiine 25 May) Migrateemr moooД л-2088010 =Setup test coverage forProphet in SonarDeployedЕ л-151110=(Deadiine 17 June) Migratedepricated Gemini models©3-20272Stefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:27...
|
46235
|
NULL
|
NULL
|
NULL
|
|
46236
|
1653
|
2
|
2026-05-15T06:53:41.186397+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828021186_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLateMoreNotion CalendarVIewJiminny ...# ji ActivityLateMoreNotion CalendarVIewJiminny ...# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya Angelova• Vasil VasilevN Stefka StovanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.#: Apps" Jira Cloud8 ToastWindowmelt@ Describe what you are looking for# releases8 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.599oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa Igithub.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stag XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumThe PFixAappLoaicMav 2026 Week20Mon iiTue 12X Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00lThe seObseonly sComr(avoicthe cano.RespThe cnulismatcl09:53 Daily -Platform11:001Preparation for 1[Support Daily, 1 Support Daily 15:00Wed1son 12Suoport Daily 15:00I| Sprint ReviewDally - Platrorm • now100% Lz• Fri 15 May 9:53:40Week vTodavSatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)Fri 151 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
-5665498472542502767
|
NULL
|
visual_change
|
ocr
|
NULL
|
ActivityLateMoreNotion CalendarVIewJiminny ...# ji ActivityLateMoreNotion CalendarVIewJiminny ...# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan TomovGalva Dimitrova. Aneliya Angelova• Vasil VasilevN Stefka StovanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovali.#: Apps" Jira Cloud8 ToastWindowmelt@ Describe what you are looking for# releases8 22Messagesr Filese Bookmarks20881): UpgiToday v iy Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master by574b5a61 - Switched deprecated get()metnoas to input and nixed merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall satesand logging0548fo%e -Y-20208 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerronShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.599oelhttns:///github.com/liminnv/oroohet/commt/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|httos://himinnv.atlassian.net/browsey-Message #releases+ Aa Igithub.com/iiminny/app/pull/12077lib2 scr2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElastiC JY-20903 Update activity stag XJY-20891 add support for second:(SRD-6853] Moxso - Potential dea" OpenSumThe PFixAappLoaicMav 2026 Week20Mon iiTue 12X Chloe Cross (Parental Leave - 256 days)Ivelina Hristova (Parental Leave - 184 days)Andrea Zlatanova (Parental Leave - 189 days)Michelle Weston (PTO - 5 davs)05:0007:00lThe seObseonly sComr(avoicthe cano.RespThe cnulismatcl09:53 Daily -Platform11:001Preparation for 1[Support Daily, 1 Support Daily 15:00Wed1son 12Suoport Daily 15:00I| Sprint ReviewDally - Platrorm • now100% Lz• Fri 15 May 9:53:40Week vTodavSatloSun 17Thu 14James Graham (PTO - 2 days)Liz Mulraney (PTO - 1 day)Fri 151 Suoport Dailv 15:001Suoport Daily 16...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46235
|
1652
|
2
|
2026-05-15T06:53:38.674006+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828018674_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelpmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)04G0С МОР Т:51 ServiclE83 Promel( Attens* МоP -(a Scherhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835Platform Team %.Q Search board8099 J1-205911 J7-2085%Ready To Be Merged (2 work tems)8 DEDatado 0 0© CursoA Sentry * X CJ Tasks© Dev3Notify the user il a SS isdeleted but is used in AJReportAКVOKTBacklogH JY-20015Upgrade BE Ibraries - MayMAINTENANEISbackiоgE JY-19958AixwownerSeiected When Setone uoa$1iTermner doesht nave the Mer leature ensoled then ther showion t oe abie to access the cota• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for help."• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying.*Note: here you can find example prompts for testing - E) Prompts and SkallsSubtasksPriorityStor...-•+0% Done1 commit11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateNone15 hours ago9:53 AM | Daily - PlatformDaily - Platform - now100% C7• Fri 15 May 9:53:3807 88• Fri 15 May 9:53Group: QuerieNSetup test coverage forProphet in SonarЕ л-151110=(Deadiine 17 June) Migratedepricated Gemini models©3-20272Stefka StoyanovaGalya DimitrovaNikolay YankovLukas Kovalik6:24...
|
NULL
|
9192752575999046503
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelpmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)04G0С МОР Т:51 ServiclE83 Promel( Attens* МоP -(a Scherhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835Platform Team %.Q Search board8099 J1-205911 J7-2085%Ready To Be Merged (2 work tems)8 DEDatado 0 0© CursoA Sentry * X CJ Tasks© Dev3Notify the user il a SS isdeleted but is used in AJReportAКVOKTBacklogH JY-20015Upgrade BE Ibraries - MayMAINTENANEISbackiоgE JY-19958AixwownerSeiected When Setone uoa$1iTermner doesht nave the Mer leature ensoled then ther showion t oe abie to access the cota• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for help."• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying.*Note: here you can find example prompts for testing - E) Prompts and SkallsSubtasksPriorityStor...-•+0% Done1 commit11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateNone15 hours ago9:53 AM | Daily - PlatformDaily - Platform - now100% C7• Fri 15 May 9:53:3807 88• Fri 15 May 9:53Group: QuerieNSetup test coverage forProphet in SonarЕ л-151110=(Deadiine 17 June) Migratedepricated Gemini models©3-20272Stefka StoyanovaGalya DimitrovaNikolay YankovLukas Kovalik6:24...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46234
|
1652
|
1
|
2026-05-15T06:53:35.609087+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828015609_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% L2• Fri 15 May 9:53:35=07 8Nikolay Yankov (Presenting)57 ServiceE3 JmlrE83 PromelAthent* MoP-XK Scher xo Curso X * Claude XС МОР Тhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835C Projects|E Datadog* CaudPlatform Team %.Q Search board$ SY-20739 / A JY-20835Ready To Be Merged (2 work tems)MCP > Enable users to get a list of deals and their detailsKAUTYOKUVv Sprint (16 work items)RLADY OR DEV 5Panorama prompts isCwOOUDUOUAAU RiPORTBacklogД JY-200763 -.=0Notify the user il a SS isdeleted but is used in AJReportAКVOKTBacklogWtowot~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Resuft: No dealsfound matching your criteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fieids whichare stored in vimininy por bt and for chow talng), acunioes (cars, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibillty settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Upgrade BE Ibraries - MayMAINTENANEISbackiоg@ JY-19958Note: here you can find example prompts for testing - E) Prompts and SkiltsSubtasks..•_ -0% DoneAixwownerSeiected When Sctone LoatrialPriorityStor...ASSRARIn Dev vI Improve Story~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commit11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateC DevSminiGroup: QueriesDEPLOY 2BERLOT(Deadiine 25 May) Migratedepricated Gemini 3.1 Flashemr mooowgoyCeД л-208801 0 =Setup test coverage forProphet in SonarMAINTENANCDeployedЕ л-151(Deadline 17 June] Migratedepricated Gemini models©3-202728• Fr 15 May 9:53L Al BookmarxsStefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:21...
|
NULL
|
459106735810992302
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% L2• Fri 15 May 9:53:35=07 8Nikolay Yankov (Presenting)57 ServiceE3 JmlrE83 PromelAthent* MoP-XK Scher xo Curso X * Claude XС МОР Тhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835C Projects|E Datadog* CaudPlatform Team %.Q Search board$ SY-20739 / A JY-20835Ready To Be Merged (2 work tems)MCP > Enable users to get a list of deals and their detailsKAUTYOKUVv Sprint (16 work items)RLADY OR DEV 5Panorama prompts isCwOOUDUOUAAU RiPORTBacklogД JY-200763 -.=0Notify the user il a SS isdeleted but is used in AJReportAКVOKTBacklogWtowot~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Resuft: No dealsfound matching your criteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fieids whichare stored in vimininy por bt and for chow talng), acunioes (cars, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibillty settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Upgrade BE Ibraries - MayMAINTENANEISbackiоg@ JY-19958Note: here you can find example prompts for testing - E) Prompts and SkiltsSubtasks..•_ -0% DoneAixwownerSeiected When Sctone LoatrialPriorityStor...ASSRARIn Dev vI Improve Story~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commit11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateC DevSminiGroup: QueriesDEPLOY 2BERLOT(Deadiine 25 May) Migratedepricated Gemini 3.1 Flashemr mooowgoyCeД л-208801 0 =Setup test coverage forProphet in SonarMAINTENANCDeployedЕ л-151(Deadline 17 June] Migratedepricated Gemini models©3-202728• Fr 15 May 9:53L Al BookmarxsStefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:21...
|
46232
|
NULL
|
NULL
|
NULL
|
|
46233
|
1653
|
1
|
2026-05-15T06:53:35.120284+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828015120_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLaterMorerireroyJiminny…..# jiminny-bg# pl ActivityLaterMorerireroyJiminny…..# jiminny-bg# platform-ticketsic productlaunches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...• Direct messages88. Stoyan TomovP Galya Dimitrova EP. Aneliya Angelova M€. Vasil VasilevA. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham "Ro Stoyan Tanev MR. Steliyan Georgiev =f Petko Kashinski. Lukas Kovali.i: AppsG Jira Cloud® ToastMistorbookmarksloolsWindowmelp# releases8 22Messagese Files• Bookmarks20881): UpgiToday~ y Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master oy(574b5a61 - Switched deprecated get()metnoas to input and nixea merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall saresand logginga548fbbe - JY-20908 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerrorShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.5991oel(https://github.com/jiminny/prophet/commit/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|(https://jiminny.atlassian.net/browse/JY-Message #releases+ Aa IC 40 lbl @ I Daily -Platform • now A # 100% €/3 • Fri 15 May 9:53:34© github.com/jimiMlibIa scro2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElasticC JY-20903 Update activity stag *JY-20891 add support for second:* (SRD-6853) Moxso - Potential dea17 OpenJY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-changePost findingsSummaryThe PR resets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmbata method and theF1xActiv1t1es0pportun1ty commana.app/Models/Activity.phpLoaic is correct. The reorderina makes sense:if (sthis-»stage id == null do sstage) (... ) 11 fallback still neededThe second if block is still needed — it handles cases where the oooortunitv didn't chanae but stage id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null . Since that branch never changes an existingopportunity, there's no stale stage risk — this asymmetry is intentional and correct.Comment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enough without it — I'd lean toward removing it per the project rules, but it's not a blocker.app/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses Sopportunity->getStageId() - the current stage of the newly matched opportunity, not thestage at the time the activity was originally imported. This is a design decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Settina the stage to the current state of the correct opportunity is the more consistent approach.This seems intentional and correct given the purpose of the command (fixing mismatched opportunities).Potential concern: Opportunity::getStageId() has a non-nullable int return type. If the opportunity somehow has anull stage id in the DB. this would fail at runtime. The command should handle this case aracefullv, e.a, catching theerror or checking for null. That said, if stage_id is always guaranteed non-null for opportunities coming from the CRMmatch, this may be acceptable....
|
NULL
|
4929803409084064287
|
NULL
|
visual_change
|
ocr
|
NULL
|
ActivityLaterMorerireroyJiminny…..# jiminny-bg# pl ActivityLaterMorerireroyJiminny…..# jiminny-bg# platform-ticketsic productlaunches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...• Direct messages88. Stoyan TomovP Galya Dimitrova EP. Aneliya Angelova M€. Vasil VasilevA. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham "Ro Stoyan Tanev MR. Steliyan Georgiev =f Petko Kashinski. Lukas Kovali.i: AppsG Jira Cloud® ToastMistorbookmarksloolsWindowmelp# releases8 22Messagese Files• Bookmarks20881): UpgiToday~ y Volume #2#512 stelivan-gGitHub APP 9:35 AM1u new commits pusnea to master oy(574b5a61 - Switched deprecated get()metnoas to input and nixea merzelogic for Lapier recuests to prevent en-Us trom Slioping in as correct languageocts4ber - Merge dranch master intoJy-20708-nx-request-handling-for-zapier642c811a - JY-20708 More tall saresand logginga548fbbe - JY-20908 Fixing to logs6604f8-2 - Y-20208 nxed svntaxerrorShow morejiminny/app Added by GitHubcirc ec APP 9-42 AMI• New commits denloved to Prophet Prod.5991oel(https://github.com/jiminny/prophet/commit/759976e18aa28d3b66030eebb36d908a92461266- Y-20881|(https://jiminny.atlassian.net/browse/JY-Message #releases+ Aa IC 40 lbl @ I Daily -Platform • now A # 100% €/3 • Fri 15 May 9:53:34© github.com/jimiMlibIa scro2 scrPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stage wiJY-20904 Fix UpdateActivityElasticC JY-20903 Update activity stag *JY-20891 add support for second:* (SRD-6853) Moxso - Potential dea17 OpenJY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-changePost findingsSummaryThe PR resets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmbata method and theF1xActiv1t1es0pportun1ty commana.app/Models/Activity.phpLoaic is correct. The reorderina makes sense:if (sthis-»stage id == null do sstage) (... ) 11 fallback still neededThe second if block is still needed — it handles cases where the oooortunitv didn't chanae but stage id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null . Since that branch never changes an existingopportunity, there's no stale stage risk — this asymmetry is intentional and correct.Comment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enough without it — I'd lean toward removing it per the project rules, but it's not a blocker.app/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses Sopportunity->getStageId() - the current stage of the newly matched opportunity, not thestage at the time the activity was originally imported. This is a design decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Settina the stage to the current state of the correct opportunity is the more consistent approach.This seems intentional and correct given the purpose of the command (fixing mismatched opportunities).Potential concern: Opportunity::getStageId() has a non-nullable int return type. If the opportunity somehow has anull stage id in the DB. this would fail at runtime. The command should handle this case aracefullv, e.a, catching theerror or checking for null. That said, if stage_id is always guaranteed non-null for opportunities coming from the CRMmatch, this may be acceptable....
|
46231
|
NULL
|
NULL
|
NULL
|
|
46232
|
1652
|
0
|
2026-05-15T06:53:31.978040+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778828011978_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% L2• Fri 15 May 9:53:31=07 8Nikolay Yankov (Presenting)57 ServiceE3 JmlrE83 PromelAthent* MoP-XK Scher xo Curso X * Claude XС МОР Тhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835C Projects|Datadog* CaudPlatform Team %.Q Search board$ SY-20739 / A JY-20835Ready To Be Merged (2 work tems)MCP > Enable users to get a list of deals and their detailsKAUTYOKUVv Sprint (16 work items)RLADY OR DEV 5Panorama prompts isCwOOUDUOUAAU RiPORTBacklogД JY-200763 -.=0Notify the user il a SS isdeleted but is used in AJReportBacklogWtowot~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Resuft: No dealsfound matching your criteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fieids whichare stored in vimininy por bt and for chow talng), acunioes (cars, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibillty settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Upgrade BE Ibraries - MayMAINTENANEISbackiоg@ JY-19958Note: here you can find example prompts for testing - E) Prompts and SkiltsSubtasks..•_ -0% DoneAixwownerSeiected When Sctone LoatrialPriorityStor...ASSRAR*xIIn Dev vI Improve Story~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commt11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateC DevSminiGroup: QueriesDEPLOY 2BERLOT(Deadiine 25 May) Migratedepricated Gemini 3.1 Flashemr moooД л-208801 0 =Setup test coverage forProphet in SonarMAINTENANCDeployedЕ л-151(Deadiine 17 June) Migratedepricated Gemini models©3-202728• Fr 15 May 9:53L Al BookmarxsStefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:18...
|
NULL
|
6800743610848202782
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comDaily - Platform - now100% L2• Fri 15 May 9:53:31=07 8Nikolay Yankov (Presenting)57 ServiceE3 JmlrE83 PromelAthent* MoP-XK Scher xo Curso X * Claude XС МОР Тhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20835C Projects|Datadog* CaudPlatform Team %.Q Search board$ SY-20739 / A JY-20835Ready To Be Merged (2 work tems)MCP > Enable users to get a list of deals and their detailsKAUTYOKUVv Sprint (16 work items)RLADY OR DEV 5Panorama prompts isCwOOUDUOUAAU RiPORTBacklogД JY-200763 -.=0Notify the user il a SS isdeleted but is used in AJReportBacklogWtowot~ DescriptionEnable customers to brainstorm in their Al tool using the information from their Jiminny deals.• allow users to search for deals through their Al and find the deals they are looking foro if nothing can be found that matches the user's search then show an appropriate error message - "Resuft: No dealsfound matching your criteria. Try searching by a different account name, adjusting the date range, or checking thedeal name in Jiminny."• allow users to get any relevant details about each deal - owner, amount, stage, account/contacts, all CRM fieids whichare stored in vimininy por bt and for chow talng), acunioes (cars, cmars)• each user should be able to access the same deals they can access in Jiminny - based on the Team Visibillty settings• Il the customer doesn't have the MCP feature enabled then they shouldn't be able to access the data:• "Error: The Jiminny MCP Connector is not avallable for your account, Please contact your Jiminny CustomerSuccess Manager or our support team for heip."|• ensure appropriate error message is shown when rate limits are hit - do we have such?• *Error: Rate limit exceeded. Too many requests have been made to the Jiminny MCP server in a short period.Please wait 60 seconds before retrying."Upgrade BE Ibraries - MayMAINTENANEISbackiоg@ JY-19958Note: here you can find example prompts for testing - E) Prompts and SkiltsSubtasks..•_ -0% DoneAixwownerSeiected When Sctone LoatrialPriorityStor...ASSRAR*xIIn Dev vI Improve Story~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch1 commt11 Create pull request |componenttPlatformSub-ProductAdd optionsLabeisNookStory point estimateC DevSminiGroup: QueriesDEPLOY 2BERLOT(Deadiine 25 May) Migratedepricated Gemini 3.1 Flashemr moooД л-208801 0 =Setup test coverage forProphet in SonarMAINTENANCDeployedЕ л-151(Deadiine 17 June) Migratedepricated Gemini models©3-202728• Fr 15 May 9:53L Al BookmarxsStefka StoyanovaGalya Dimitrova3 othersNikolay Yankov9:53 AM | Daily - PlatformLukas Kovalik6:18...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46215
|
1650
|
61
|
2026-05-15T06:52:48.070105+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827968070_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesActivit FirefoxFileEditViewHistoryBookmarksProfilesActivity MonitorAll ProcessesProcess NameWindowServerPostman Helper (Renderer)Firefox GPU HelperFirefoxFirefox GPU HelperFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentPostmanSlack Helper (Renderer)FirefoxCP Isolated Web ContentFirefoxFirefoxCP Isolated Web ContentNotion Calendar Helper (Renderer)Notion Helper (Renderer)FirefoxCP Isolated Web ContentscreenpipeiTerm2Notion Calendar Helper (GPU)RaycastClaude Helper (Renderer)Claude HelperFirefoxCP Isolated Web ContentFinderFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentClaudeToolsMem..Threads3,24 GB1 022,7 MB974,2 MB855,1 MB825,9 MB762,0 MB744,4 MB736,7 MB673,2 MB502,8 MB437,5 MB436,3 MB354,2 MB341,1 MB335,1 MB305,2 MB286,9 MB258,0 MB256,4 MB246,6 MB231,9 MB208,6 MB208,6 MB208,1 MB206,2 MB193,8 MB187,0 MB185,3 MB WindowHelpCPU(ahlDaily - Platform • now100% <28 • Fri 15 May 9:52:47Ports PID MEMORY PRESSUREMemoryUser_windowserverlukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukasEnergyDiskNetworkQ Search!Physical Memory:Memory Used:Cached Files:Swap Used:16,00 GB14,32 GB1.62 GB2,72 GBApp Memory:Wired Memory:Compressed:3,23 GB4,38 GB6,16 GB5:33...
|
NULL
|
-991729109462393016
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksProfilesActivit FirefoxFileEditViewHistoryBookmarksProfilesActivity MonitorAll ProcessesProcess NameWindowServerPostman Helper (Renderer)Firefox GPU HelperFirefoxFirefox GPU HelperFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentPostmanSlack Helper (Renderer)FirefoxCP Isolated Web ContentFirefoxFirefoxCP Isolated Web ContentNotion Calendar Helper (Renderer)Notion Helper (Renderer)FirefoxCP Isolated Web ContentscreenpipeiTerm2Notion Calendar Helper (GPU)RaycastClaude Helper (Renderer)Claude HelperFirefoxCP Isolated Web ContentFinderFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentFirefoxCP Isolated Web ContentClaudeToolsMem..Threads3,24 GB1 022,7 MB974,2 MB855,1 MB825,9 MB762,0 MB744,4 MB736,7 MB673,2 MB502,8 MB437,5 MB436,3 MB354,2 MB341,1 MB335,1 MB305,2 MB286,9 MB258,0 MB256,4 MB246,6 MB231,9 MB208,6 MB208,6 MB208,1 MB206,2 MB193,8 MB187,0 MB185,3 MB WindowHelpCPU(ahlDaily - Platform • now100% <28 • Fri 15 May 9:52:47Ports PID MEMORY PRESSUREMemoryUser_windowserverlukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukaslukasEnergyDiskNetworkQ Search!Physical Memory:Memory Used:Cached Files:Swap Used:16,00 GB14,32 GB1.62 GB2,72 GBApp Memory:Wired Memory:Compressed:3,23 GB4,38 GB6,16 GB5:33...
|
46212
|
NULL
|
NULL
|
NULL
|
|
46187
|
1651
|
22
|
2026-05-15T06:51:34.143785+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827894143_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Jiminny...~# jiminny-bg# platform-tickets# product Jiminny...~# jiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8P. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira CloudToastQ Describe what you are looking forToastHomeAboutWeanesday, May 15thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-18091|Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolavbiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflicts#11443 lest hubletslatency5 months old • 20 hles+ Aa €• github.oMlib• scro• NewPlatform Sprint 4 Q2 - Platform TeJY-20903 Update activity stag XJY-20904 Fix UpdateActivityElastic• JY-20903 Update activity stage wf. JY-20891 add support for seconda* (SRD-6853) Moxso - Potential deaActivityFilesMore‹ $0 lil• I Daily -Platform • nowX 100% C/ 8 • Fri 15 May 9:51:33.JY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-changeSummaryThe PRresets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmData method and theFixActivities0pportunity command.app/Models/Activity.phpLogic is correct. The reordering makes sense:// Before: only set stage if null (no reset on opportunity change)1T (sch1s→>Stage 10 === null dd Sstage) 1 ... Jif (Sopportunity && Sthis->opportunity_id !== Sopportunity→>id) { ... }// After: reset stage when opportunity changes, then fallback for null stage_idif (Sopportunity && $this->opportunity_id !== $opportunity->id) {pines-popportundlyde= sopportunalyeedSthis->stade id = Sstage?->id: // mav null out stage idThe second if block is still needed — it handles cases where the opportunity didn't change but stage id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null. Since that branch never changes an existingonnortunitv there's no stale stage risk — this asvmmetrv is intentional and correctiComment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enouah without it — I'd lean toward removina it ner the proiect rules but it's not a blockerlapp/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses $opportunity->getStageId() - the current stage of the newly matched opportunity, not thestage at the time the activity was oriainallv imported. This is a desian decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Setting the stage to the current state of the correct opportunity is the more consistent approach.This seems intentional and correct given the purpose of the command (fixing mismatched opportunities)Potential concern: Ooportunitv::getStageld() has anon-nullable int return tvpe. If the opportunity somehow has alnull stage_id in the DB, this would fail at runtime. The command should handle this case gracefully, e.g. catching theerror or checking for null. That said, if stage_id is always guaranteed non-null for opportunities coming from the CRMmatch this mav he accentableTest Coverage...
|
NULL
|
877800946412561806
|
NULL
|
click
|
ocr
|
NULL
|
Jiminny...~# jiminny-bg# platform-tickets# product Jiminny...~# jiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8P. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira CloudToastQ Describe what you are looking forToastHomeAboutWeanesday, May 15thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-18091|Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolavbiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflicts#11443 lest hubletslatency5 months old • 20 hles+ Aa €• github.oMlib• scro• NewPlatform Sprint 4 Q2 - Platform TeJY-20903 Update activity stag XJY-20904 Fix UpdateActivityElastic• JY-20903 Update activity stage wf. JY-20891 add support for seconda* (SRD-6853) Moxso - Potential deaActivityFilesMore‹ $0 lil• I Daily -Platform • nowX 100% C/ 8 • Fri 15 May 9:51:33.JY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-changeSummaryThe PRresets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmData method and theFixActivities0pportunity command.app/Models/Activity.phpLogic is correct. The reordering makes sense:// Before: only set stage if null (no reset on opportunity change)1T (sch1s→>Stage 10 === null dd Sstage) 1 ... Jif (Sopportunity && Sthis->opportunity_id !== Sopportunity→>id) { ... }// After: reset stage when opportunity changes, then fallback for null stage_idif (Sopportunity && $this->opportunity_id !== $opportunity->id) {pines-popportundlyde= sopportunalyeedSthis->stade id = Sstage?->id: // mav null out stage idThe second if block is still needed — it handles cases where the opportunity didn't change but stage id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null. Since that branch never changes an existingonnortunitv there's no stale stage risk — this asvmmetrv is intentional and correctiComment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enouah without it — I'd lean toward removina it ner the proiect rules but it's not a blockerlapp/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses $opportunity->getStageId() - the current stage of the newly matched opportunity, not thestage at the time the activity was oriainallv imported. This is a desian decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Setting the stage to the current state of the correct opportunity is the more consistent approach.This seems intentional and correct given the purpose of the command (fixing mismatched opportunities)Potential concern: Ooportunitv::getStageld() has anon-nullable int return tvpe. If the opportunity somehow has alnull stage_id in the DB, this would fail at runtime. The command should handle this case gracefully, e.g. catching theerror or checking for null. That said, if stage_id is always guaranteed non-null for opportunities coming from the CRMmatch this mav he accentableTest Coverage...
|
46185
|
NULL
|
NULL
|
NULL
|
|
46164
|
1650
|
27
|
2026-05-15T06:50:00.770106+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827800770_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Hidden Bar+(ahl| Daily - Platform • now100% <78 Hidden Bar+(ahl| Daily - Platform • now100% <78• Fri 15 May 9:50:00meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com0m 8Nikolay Yankov (Presenting)5 ServiceE83 PromelAtent83 MCP -(a Schemhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20846C Projects|E DatadogPlatform Team %.Q Search boards009 J1-207591 1 J7-29840v Ready To Be Merged 12 work temsMCP > Enable the AI to know details about the userRAUTYOK UEYSprint (16 work items)RLADY JOR DEV 5Panorama prompts isCWOOUDUUAAJREPORTSBacklogP Jy-200763 .=0~ DescriptionEnable the AI tool to know the details about the user that is asking the questions. It will use those detalls to know how tofilter the calls and deals.• provide the Al a tool that gives insights about the user - name, emall, team esc.• il the customer doesn't have the MCP feature enabled then they should be able to access the data:o use a feature fiag for the check - "MCP" add to Technical Setings for now• "Error: The Jiminny MCP Connector is not avallable for your account. Please contact your Jiminny CustomerSuccess Manager or our support team for heip."Notify the user it a SS isdeleted but is used in AJReportAКYOKTBacklogSubtasks***_T100% DoneAssignee9 JY-20848 Implement get.me= Medium$ JY-20849 manualtestingNikolay LNkclay I...Upgrade BE Ibraries - MayMAINTENANCISbackiоg@ JY-19958= MediumNkolay L.9 Jy-20877address feedback for the toolstructure= MediumNikolay Y...Linked work itemsAdd linked work itemAixwownerooSelected When Sctont Loatrial9:50 AM | Daily - Platform8• Fri 16 May 9:50o Curso X* ClaudeMOPTinsights & Coachin.0 Dev3x Improve StoryStefka StoyanovaNikolay IvanovCode Review~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch8 commits1 pull request1 buildwomponentPlatformSub-ProductAdd optionsLabelsstory point esomat14 hours agoOPENBEPLOT(Deadiine 25 May) Migratedepricated Gemini 3.1 Flashemora moooWepoTreД л-г0в10Setup test coverage forProphet in SonarDeployed8-л1-19051(Deadiine 17 June] Migratedepricated Gemini models3 othersGalya Dimitrova•..Lukas Kovalik2:46...
|
NULL
|
-2139788052421952243
|
NULL
|
visual_change
|
ocr
|
NULL
|
Hidden Bar+(ahl| Daily - Platform • now100% <78 Hidden Bar+(ahl| Daily - Platform • now100% <78• Fri 15 May 9:50:00meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com0m 8Nikolay Yankov (Presenting)5 ServiceE83 PromelAtent83 MCP -(a Schemhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20846C Projects|E DatadogPlatform Team %.Q Search boards009 J1-207591 1 J7-29840v Ready To Be Merged 12 work temsMCP > Enable the AI to know details about the userRAUTYOK UEYSprint (16 work items)RLADY JOR DEV 5Panorama prompts isCWOOUDUUAAJREPORTSBacklogP Jy-200763 .=0~ DescriptionEnable the AI tool to know the details about the user that is asking the questions. It will use those detalls to know how tofilter the calls and deals.• provide the Al a tool that gives insights about the user - name, emall, team esc.• il the customer doesn't have the MCP feature enabled then they should be able to access the data:o use a feature fiag for the check - "MCP" add to Technical Setings for now• "Error: The Jiminny MCP Connector is not avallable for your account. Please contact your Jiminny CustomerSuccess Manager or our support team for heip."Notify the user it a SS isdeleted but is used in AJReportAКYOKTBacklogSubtasks***_T100% DoneAssignee9 JY-20848 Implement get.me= Medium$ JY-20849 manualtestingNikolay LNkclay I...Upgrade BE Ibraries - MayMAINTENANCISbackiоg@ JY-19958= MediumNkolay L.9 Jy-20877address feedback for the toolstructure= MediumNikolay Y...Linked work itemsAdd linked work itemAixwownerooSelected When Sctont Loatrial9:50 AM | Daily - Platform8• Fri 16 May 9:50o Curso X* ClaudeMOPTinsights & Coachin.0 Dev3x Improve StoryStefka StoyanovaNikolay IvanovCode Review~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch8 commits1 pull request1 buildwomponentPlatformSub-ProductAdd optionsLabelsstory point esomat14 hours agoOPENBEPLOT(Deadiine 25 May) Migratedepricated Gemini 3.1 Flashemora moooWepoTreД л-г0в10Setup test coverage forProphet in SonarDeployed8-л1-19051(Deadiine 17 June] Migratedepricated Gemini models3 othersGalya Dimitrova•..Lukas Kovalik2:46...
|
46162
|
NULL
|
NULL
|
NULL
|
|
46163
|
1651
|
15
|
2026-05-15T06:49:55.319302+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827795319_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
оаж0B, SO 1 Daily-Platform- nowX 100% C/ • Fr оаж0B, SO 1 Daily-Platform- nowX 100% C/ • Fri 15 May 9:49:54.Jiminny... ~# jiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8P. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira CloudToastQ Describe what you are looking forToastHomeAboutWeanesday, May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-18091|Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolavbiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflicts#11443 lest hubletslatencys months old • 20 hles+ Aa €© github.com/jiminny/app/pull/12077Mlib• scro• NewPlatform Sprint 4 Q2 - Platform TeJY-20903 Update activity stag XJY-20904 Fix UpdateActivityElastic• JY-20903 Update activity stage wf. JY-20891 add support for seconda* (SRD-6853) Moxso - Potential dea87 OpenJY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-change3 participants8 Lock conversationActivityFilesMorecoce review• Gather context|Review changed filesPost findingsSummaryThe PR resets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmbata method and theF1xActivitlesOpportunity command.app/Models/Activity.phpLogic is correct. The reordering makes sense:If (sthis-sstage_id == null d& sstage) ( .... X 11 fallback still neededThe second if block is still needed — it handles cases where the opportunity didn't change but stage_id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null . Since that branch never changes an existingopportunity, there's no stale stage risk — this asymmetry is intentional and correct.Comment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enough without it - I'd lean toward removing it per the project rules, but it's not a blocker.app/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses Sopportunity->getStageld() - the current stage of the newly matched opportunity, not thestage at the time the activity was originally imported. This is a design decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Setting the stage to the current state of the correct onportunity is the more consistent approach....
|
NULL
|
-3561315826985819472
|
NULL
|
visual_change
|
ocr
|
NULL
|
оаж0B, SO 1 Daily-Platform- nowX 100% C/ • Fr оаж0B, SO 1 Daily-Platform- nowX 100% C/ • Fri 15 May 9:49:54.Jiminny... ~# jiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8P. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira CloudToastQ Describe what you are looking forToastHomeAboutWeanesday, May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-18091|Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolavbiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflicts#11443 lest hubletslatencys months old • 20 hles+ Aa €© github.com/jiminny/app/pull/12077Mlib• scro• NewPlatform Sprint 4 Q2 - Platform TeJY-20903 Update activity stag XJY-20904 Fix UpdateActivityElastic• JY-20903 Update activity stage wf. JY-20891 add support for seconda* (SRD-6853) Moxso - Potential dea87 OpenJY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-change3 participants8 Lock conversationActivityFilesMorecoce review• Gather context|Review changed filesPost findingsSummaryThe PR resets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmbata method and theF1xActivitlesOpportunity command.app/Models/Activity.phpLogic is correct. The reordering makes sense:If (sthis-sstage_id == null d& sstage) ( .... X 11 fallback still neededThe second if block is still needed — it handles cases where the opportunity didn't change but stage_id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null . Since that branch never changes an existingopportunity, there's no stale stage risk — this asymmetry is intentional and correct.Comment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enough without it - I'd lean toward removing it per the project rules, but it's not a blocker.app/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses Sopportunity->getStageld() - the current stage of the newly matched opportunity, not thestage at the time the activity was originally imported. This is a design decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Setting the stage to the current state of the correct onportunity is the more consistent approach....
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46162
|
1650
|
26
|
2026-05-15T06:49:54.674440+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827794674_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Hidden Bar+(ahlmeet.google.com/mie-gawc-dsi?authus Hidden Bar+(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com| Daily - Platform • now100% <78• Fri 15 May 9:49:540л 8Nikolay Yankov (Presenting)51 Service* PromeAthent83 MCP -Ca Scherhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20846E DatadogPlatform Team %.Q Search boards00$ SY-20739 / A JY-20846Ready To Be Merged (2 work tema)MCP > Enable the AI to know details about the userO AUTYOKUVv Sprint (16 work itema)RLADY JOK DEV 5Panorama prompts isCwooUDUouAAJREPORTSBacklogД Sy-206763 *ea+=~ DescriptionEnable the AI tool to know the details about the user that is asking the questions. It will use those details to know how tofilter the calls and deals.• provide the Al a tool that gives insights about the user - name, emall, team esc.• Il the customer doesn't have the MCP feature enabled then they should be able to access the data:o use a feature fiag for the check - "MCP" add to Technical Settings for now• "Error: The Jiminny MCP Connector is not avallable for your account. Please contact your Jiminny CustomerSuccess Manager or our support team for heip."Notify the user it a SS isdeleted but is used in AJReportAWErOKTBacklogJy-20615Subtasks***_ TAssignee% JY-20848 implement get.me= Medium9 JY-20849 manualtestingUpgrade BE Ibraries - MayMAINTENANEISbackiюgE JY-19958= MediumNikolay L..Nkclay I...Nkolay I.9Jy-20877address feedback for the toolstructure= Medium• Nikolay V....Linked work itemsAdd linked work itemAixwownerooSciected When Sctonx Loatrial9:49 AM | Daily - Platformo Curso X* Claude*xICode Review~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch8 commits1 pull request1 bulldwomponontPlatformSub-ProductAdd optionsLabetsstory point esomat•. 00MOPTinsights & Coachin.0 Dev8• Fri 15 May 9:403x Improve Story14 hours agoOPENGroup: QueriesBERLOT(Deadline 25 May) MigrateenoramoooWpoTreД л-20010Setup test coverage forProphet in SonarDeployedВ л-1051(Deadline 17 June] Migratedepricated Gemini modelsStetka Stoyanova,Nikolay Ivanov3 othersGalya Dimitrova•..Lukas Kovalik2:40...
|
NULL
|
-5165831143336809113
|
NULL
|
visual_change
|
ocr
|
NULL
|
Hidden Bar+(ahlmeet.google.com/mie-gawc-dsi?authus Hidden Bar+(ahlmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com| Daily - Platform • now100% <78• Fri 15 May 9:49:540л 8Nikolay Yankov (Presenting)51 Service* PromeAthent83 MCP -Ca Scherhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-20846E DatadogPlatform Team %.Q Search boards00$ SY-20739 / A JY-20846Ready To Be Merged (2 work tema)MCP > Enable the AI to know details about the userO AUTYOKUVv Sprint (16 work itema)RLADY JOK DEV 5Panorama prompts isCwooUDUouAAJREPORTSBacklogД Sy-206763 *ea+=~ DescriptionEnable the AI tool to know the details about the user that is asking the questions. It will use those details to know how tofilter the calls and deals.• provide the Al a tool that gives insights about the user - name, emall, team esc.• Il the customer doesn't have the MCP feature enabled then they should be able to access the data:o use a feature fiag for the check - "MCP" add to Technical Settings for now• "Error: The Jiminny MCP Connector is not avallable for your account. Please contact your Jiminny CustomerSuccess Manager or our support team for heip."Notify the user it a SS isdeleted but is used in AJReportAWErOKTBacklogJy-20615Subtasks***_ TAssignee% JY-20848 implement get.me= Medium9 JY-20849 manualtestingUpgrade BE Ibraries - MayMAINTENANEISbackiюgE JY-19958= MediumNikolay L..Nkclay I...Nkolay I.9Jy-20877address feedback for the toolstructure= Medium• Nikolay V....Linked work itemsAdd linked work itemAixwownerooSciected When Sctonx Loatrial9:49 AM | Daily - Platformo Curso X* Claude*xICode Review~ DetailsAssigneeNkolay IvanowAssign to me2 Galya DimitrovaDevelopmentQ Open with VS Code1 branch8 commits1 pull request1 bulldwomponontPlatformSub-ProductAdd optionsLabetsstory point esomat•. 00MOPTinsights & Coachin.0 Dev8• Fri 15 May 9:403x Improve Story14 hours agoOPENGroup: QueriesBERLOT(Deadline 25 May) MigrateenoramoooWpoTreД л-20010Setup test coverage forProphet in SonarDeployedВ л-1051(Deadline 17 June] Migratedepricated Gemini modelsStetka Stoyanova,Nikolay Ivanov3 othersGalya Dimitrova•..Lukas Kovalik2:40...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46110
|
1649
|
60
|
2026-05-15T06:47:54.487917+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827674487_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Home1839MoreJiminny... ~# jiminny-bg# platform-tic Home1839MoreJiminny... ~# jiminny-bg# platform-tickets# product_launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8P. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil VasilevA. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i# AppsG Jira CloudToastQ Describe what you are looking forToastAboutWednesday, May 13th~approved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-18091|Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolaybiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflictsapp#11443 Test hubletslatency5 months old • 20 files_+ Aa ®• NewMlibPlatform Sprint 4 Q2 - Platform TeD scro• Jy-20904 Fix UodateActivitvElastiJY-20903 Update activity stage wiC. JY-20891 add support for seconda* (SRD-6853) Moxso - Potential x< S0 liil © I Daily - Platform - nowinny.allasslan.netlracustom/37/SRD-6853O JIMINNY@ For you© Recenti Starred8$ Apps0, Spaces+...? Jiminny (New)Q Service-DeskE Queues- ..•Team Priorityf All open tickets 15@ Unassigned t... 5E Support tea...• Raised by me@ Assigned to ...@ Service requ...1E Platform team@ Processing t...Site reliability... Of New features... O@ InfoSec issues 0# Ready for Cu... O@ Resolved ti.. 999+= View all queuesE Service requestsA Incidentsbl Reports@ OperationsA Knowledge Base0 CustomersChannelsEmail logs%> Developer escalationsiIs Slack integration& Reporting CenterQ Search+ Create< BackX* SRD-6853Moxso - Potential deal stages bugi Link work item ?v|¿ Add form+ Escalate work itemD Add designCreate v..GD Gabriela Dureva raised this request via JiraDescriptionHi team,Moxso flaqged that the following conversation was recorded while the deal was still at the Discovery stage:https://app.jiminny.eu/playback/975c6830-7d49-4cle-b2e9-ac80c10a738aShortly after the call ended, the rep updated the deal stage to Closed Lost. The issue is that when the client uses the Stage at Call filter in On Demand and selects Discovery, this recording doesnot aooear.Would we be able to check what the deal stage was at the time the recording took place, and whether there may be a bug causing the recording not to show up under the Stage at Call - Discoveryfilter?Thank vou.Gabbysteps to reproaucenraImpactNoneRoot causeNoneACtIVItV•HistorvWork lodAporovals• Summarise 2 comments =Add internal notelReniv to customeiPro tip: press M to comment)Lukas Kovalik 21 hours ago & Internal noteThe activity was matched to another opportunity 253868114162 also called nordhusene.dk1 [2826-84-26 03:14:821 production.INF0: [Calendar] Updated activity cam data ("activity_id": "975C6830-7d49-4c-b2e9-ac88c10a738a", "origina_data"100% K/2 8 • Fri 15 May 9:47:54Ask RovoIn ProgressDetailsAssignee@ Lukas KovalikReporterGD Gabriela DurevaRequest TypeNoneKnowledge base # View related art...Type of Infosec incidentNonePriority level(P2 MediumComponents(InfoSec)NoneComponentsNoneExpected outcomeThe recording shows when the client selectsStage at call - discoveryActual outcomen/aData Centre(EUDev TeamPlatform teamCustomer typeMid MarketSeverity levels2...
|
NULL
|
-1475280820253931758
|
NULL
|
click
|
ocr
|
NULL
|
Home1839MoreJiminny... ~# jiminny-bg# platform-tic Home1839MoreJiminny... ~# jiminny-bg# platform-tickets# product_launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8P. Stoyan TomovP Galya Dimitrova E. Aneliya Angelova •€. Vasil VasilevA. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i# AppsG Jira CloudToastQ Describe what you are looking forToastAboutWednesday, May 13th~approved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-18091|Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolaybiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflictsapp#11443 Test hubletslatency5 months old • 20 files_+ Aa ®• NewMlibPlatform Sprint 4 Q2 - Platform TeD scro• Jy-20904 Fix UodateActivitvElastiJY-20903 Update activity stage wiC. JY-20891 add support for seconda* (SRD-6853) Moxso - Potential x< S0 liil © I Daily - Platform - nowinny.allasslan.netlracustom/37/SRD-6853O JIMINNY@ For you© Recenti Starred8$ Apps0, Spaces+...? Jiminny (New)Q Service-DeskE Queues- ..•Team Priorityf All open tickets 15@ Unassigned t... 5E Support tea...• Raised by me@ Assigned to ...@ Service requ...1E Platform team@ Processing t...Site reliability... Of New features... O@ InfoSec issues 0# Ready for Cu... O@ Resolved ti.. 999+= View all queuesE Service requestsA Incidentsbl Reports@ OperationsA Knowledge Base0 CustomersChannelsEmail logs%> Developer escalationsiIs Slack integration& Reporting CenterQ Search+ Create< BackX* SRD-6853Moxso - Potential deal stages bugi Link work item ?v|¿ Add form+ Escalate work itemD Add designCreate v..GD Gabriela Dureva raised this request via JiraDescriptionHi team,Moxso flaqged that the following conversation was recorded while the deal was still at the Discovery stage:https://app.jiminny.eu/playback/975c6830-7d49-4cle-b2e9-ac80c10a738aShortly after the call ended, the rep updated the deal stage to Closed Lost. The issue is that when the client uses the Stage at Call filter in On Demand and selects Discovery, this recording doesnot aooear.Would we be able to check what the deal stage was at the time the recording took place, and whether there may be a bug causing the recording not to show up under the Stage at Call - Discoveryfilter?Thank vou.Gabbysteps to reproaucenraImpactNoneRoot causeNoneACtIVItV•HistorvWork lodAporovals• Summarise 2 comments =Add internal notelReniv to customeiPro tip: press M to comment)Lukas Kovalik 21 hours ago & Internal noteThe activity was matched to another opportunity 253868114162 also called nordhusene.dk1 [2826-84-26 03:14:821 production.INF0: [Calendar] Updated activity cam data ("activity_id": "975C6830-7d49-4c-b2e9-ac88c10a738a", "origina_data"100% K/2 8 • Fri 15 May 9:47:54Ask RovoIn ProgressDetailsAssignee@ Lukas KovalikReporterGD Gabriela DurevaRequest TypeNoneKnowledge base # View related art...Type of Infosec incidentNonePriority level(P2 MediumComponents(InfoSec)NoneComponentsNoneExpected outcomeThe recording shows when the client selectsStage at call - discoveryActual outcomen/aData Centre(EUDev TeamPlatform teamCustomer typeMid MarketSeverity levels2...
|
46106
|
NULL
|
NULL
|
NULL
|
|
46108
|
1648
|
47
|
2026-05-15T06:47:54.457735+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827674457_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
+FirefoxFileEditViewHistoryBookmarksProfilesToolsW +FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahl→Cmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)Tớt51 ServiceE3 JminE83 PrompsAttent* MoP•X Scher Xo CursoX* Ciaude xhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-18091C Projects|Datadog ©* CauờiPlatform Team %.Q Search board9 J1-103221 2 J7-15051Ready To Be Merged (2 wock tema)Upgrade to PHP 8.5KAUTYOK UVSprint (16 work items)~ DescriptionREADY JOR DEV SBranchInitial ReleaseActive Support UntilSecurity Support Until23 Nov 202331 Dec 202531 Dec 2027Panorama prompts isCWoOOUDUAAJ REPORTSBacklogД JY-200763 •e0+=21 Nov 202431 Dec 202631 Dec 202831 Dec 202731 Dec 2029Notify the user it a SS isdeleted but is used in AJReportAKrOKTBacklogCurrenty the Jiminny app is on PHP 8.3 which is 2 versions behind the latest one. It is already stable as was releasedcouple of months ago, so please proceed with an update.Here are Migration Guides:PHP: Migrating from PHP 8.3.x to PHP 8.4x - Manual• PHP: Migrating from PHP 8.4.x 10 PHP 8.5x - ManualSubtasksUpgrade BE Ibraries - MayMAINTENANEDAdd subtaskBackiюgLinked work items@ Jy-19058Q JY-20902 Test upgrade of PHP 8,5BACKLOGAlew owneroSeiccted Whien setuneuoatrial9:47 AM | Daily - PlatformС МОР Т/insights & Coachin.0 DevReady for QAsx improve Techrical Story~ DetailsAssigneeNikolay IvanovAssign to me@ Martin PeckovDevelopment &Q Open with VS Code2 branches16 commit2 days ago +COVUIT#18be2e0|+15 more commitsAdd optionsLabels→| Daily - Platform • now100% <78• Fri 15 May 9:47:54=07 8SimiriGroup: QueriesDEPLOY 2DeRLOT[Deadline 25 May) Migratedepricated Gemini 3.1 Flashemoroa moooД л-20880Setup test coverage forProphet in SonarMASNTENANCEDeployed8л1-19051(Deadiine 17 June) Migratedepricated Gemini models0=18• Fri 15 May 9:47L Al BookmarxsNikolay YankovAneliya Angelova3 othersSteliyan GeorgievLukas Kovalik0:40...
|
NULL
|
6997780539561612685
|
NULL
|
click
|
ocr
|
NULL
|
+FirefoxFileEditViewHistoryBookmarksProfilesToolsW +FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(ahl→Cmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)Tớt51 ServiceE3 JminE83 PrompsAttent* MoP•X Scher Xo CursoX* Ciaude xhttps://fiminny.atlassian.net/jra/software/c/projects/JJY/boards/37?selectedissue=JY-18091C Projects|Datadog ©* CauờiPlatform Team %.Q Search board9 J1-103221 2 J7-15051Ready To Be Merged (2 wock tema)Upgrade to PHP 8.5KAUTYOK UVSprint (16 work items)~ DescriptionREADY JOR DEV SBranchInitial ReleaseActive Support UntilSecurity Support Until23 Nov 202331 Dec 202531 Dec 2027Panorama prompts isCWoOOUDUAAJ REPORTSBacklogД JY-200763 •e0+=21 Nov 202431 Dec 202631 Dec 202831 Dec 202731 Dec 2029Notify the user it a SS isdeleted but is used in AJReportAKrOKTBacklogCurrenty the Jiminny app is on PHP 8.3 which is 2 versions behind the latest one. It is already stable as was releasedcouple of months ago, so please proceed with an update.Here are Migration Guides:PHP: Migrating from PHP 8.3.x to PHP 8.4x - Manual• PHP: Migrating from PHP 8.4.x 10 PHP 8.5x - ManualSubtasksUpgrade BE Ibraries - MayMAINTENANEDAdd subtaskBackiюgLinked work items@ Jy-19058Q JY-20902 Test upgrade of PHP 8,5BACKLOGAlew owneroSeiccted Whien setuneuoatrial9:47 AM | Daily - PlatformС МОР Т/insights & Coachin.0 DevReady for QAsx improve Techrical Story~ DetailsAssigneeNikolay IvanovAssign to me@ Martin PeckovDevelopment &Q Open with VS Code2 branches16 commit2 days ago +COVUIT#18be2e0|+15 more commitsAdd optionsLabels→| Daily - Platform • now100% <78• Fri 15 May 9:47:54=07 8SimiriGroup: QueriesDEPLOY 2DeRLOT[Deadline 25 May) Migratedepricated Gemini 3.1 Flashemoroa moooД л-20880Setup test coverage forProphet in SonarMASNTENANCEDeployed8л1-19051(Deadiine 17 June) Migratedepricated Gemini models0=18• Fri 15 May 9:47L Al BookmarxsNikolay YankovAneliya Angelova3 othersSteliyan GeorgievLukas Kovalik0:40...
|
46107
|
NULL
|
NULL
|
NULL
|
|
46088
|
1648
|
35
|
2026-05-15T06:47:00.855005+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827620855_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
+FirefoxFileEditViewHistoryBookmarksProfilesToolsW +FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelplhl→meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)57 ServiceE3 JminrE3 Promp:( Attent* McP•XK Schemo Curso X* Claude XI0. 00С МОР Т:https://fiminny.atlassian.net/jra/software/c/projects/JY/boards/37?selectedissue=JY-20361C Projects|DatadogPlatform Team %.Q Search boardS009J1-19S091 1 J7-20301Ready To Be Merged (2 work tems)Linked work itemsAdd linked work itemReady To MergeOAUTYOK UV3x Improve Story~ ActivityWork log~ DetailsSuggest a replyStatus update...Thanks.Assignee& Aneliya AngelovaAssign to mePro tipc press M to com2 Galya Dimitrova8Develcomen13 May 2026 at 08:08Compieted in sprint 3: 2 daysQ Open with VS Codev Sprint (16 work items)1 branch7 commitsStellyan Georgiev1 pull requestNotify the user it a13 May 2026 at 07:20Panocamy oromots3 buldsdeleted but is used in AJ..& rested tis on tin and k looks ike working tine to me.AJREPORTSP Jy-20676Releases(4) Undefined environment2 See all deployments8. Ask Jiminmy• Clear chae |® Manage promptsPromot fibraryNotify the user it a SS isocrered outis useoinAReportAJREPORTSBacklogwomonerPlatformSub-ProductC +Y-20903In Devn = 0Е-л-180019:47 AM | Daily - Platform• De2 days agcOPEN| Daily - Platform • nowAll-In-OneC.Capture AreaCapture Previous AreaCapture FullscreenCapture WindowScrolling Capture• Self-TimerAa Capture Text (OCR)• Record ScreenHide Desktop IconsOpen..& Pin to the Screen...Capture History...About CleanShot...Check for Updates...Settings...Quit(Deadiine 25 May) Migrateohorcare Cminilashwtcornoeoto+85+₴3TKTOTRTB28,nkov100% C8•Fri 15 May 9:47:00••8Stefka Stoyanova3 otherseorgievLukas Kovalik...
|
NULL
|
1025791575023550102
|
NULL
|
visual_change
|
ocr
|
NULL
|
+FirefoxFileEditViewHistoryBookmarksProfilesToolsW +FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelplhl→meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)57 ServiceE3 JminrE3 Promp:( Attent* McP•XK Schemo Curso X* Claude XI0. 00С МОР Т:https://fiminny.atlassian.net/jra/software/c/projects/JY/boards/37?selectedissue=JY-20361C Projects|DatadogPlatform Team %.Q Search boardS009J1-19S091 1 J7-20301Ready To Be Merged (2 work tems)Linked work itemsAdd linked work itemReady To MergeOAUTYOK UV3x Improve Story~ ActivityWork log~ DetailsSuggest a replyStatus update...Thanks.Assignee& Aneliya AngelovaAssign to mePro tipc press M to com2 Galya Dimitrova8Develcomen13 May 2026 at 08:08Compieted in sprint 3: 2 daysQ Open with VS Codev Sprint (16 work items)1 branch7 commitsStellyan Georgiev1 pull requestNotify the user it a13 May 2026 at 07:20Panocamy oromots3 buldsdeleted but is used in AJ..& rested tis on tin and k looks ike working tine to me.AJREPORTSP Jy-20676Releases(4) Undefined environment2 See all deployments8. Ask Jiminmy• Clear chae |® Manage promptsPromot fibraryNotify the user it a SS isocrered outis useoinAReportAJREPORTSBacklogwomonerPlatformSub-ProductC +Y-20903In Devn = 0Е-л-180019:47 AM | Daily - Platform• De2 days agcOPEN| Daily - Platform • nowAll-In-OneC.Capture AreaCapture Previous AreaCapture FullscreenCapture WindowScrolling Capture• Self-TimerAa Capture Text (OCR)• Record ScreenHide Desktop IconsOpen..& Pin to the Screen...Capture History...About CleanShot...Check for Updates...Settings...Quit(Deadiine 25 May) Migrateohorcare Cminilashwtcornoeoto+85+₴3TKTOTRTB28,nkov100% C8•Fri 15 May 9:47:00••8Stefka Stoyanova3 otherseorgievLukas Kovalik...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46085
|
1648
|
33
|
2026-05-15T06:46:57.826310+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827617826_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryWindowlahl→Q.C 4 Meet - FirefoxFileEditViewHistoryWindowlahl→Q.C 4 Meet - Daily - Platform+ New TabBookmarksProfilesToolsHelpmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)I7 Sevio0 ProjectsE ANs3 59Platform Team200JY-TS00OJT-S0%v Ready To Be Merged (2 work temwurnwswtewterBasxosД Jy-20678wwrwwwreosnМRIRRTAJ Panorama for Call Scoring in OD~ DescriptionCurrently AJ Panorama in O0 allows managers to get insights about the pertormance of their team. We have now asded afunctionaity for AJ Caili Scoring that aiso provides insights about the performance. It wi be good to leverage both of themIn the chat so that managers can oet the best resuits)• Include the Call Score information for each call in Panorama• the cortext should include - total score, score card name, individual rules score, scoring crteria (the customer'sprompt for the ruie). usttication, timestamp. This information is stored in the ESy Ahachments...-Dute aoded +Screensnol 2040705-15 119.6.42 p0SubtasksAdd subtaskLinked work kemsAoeiedwartem~ ActivityO ar-ososn=0Bacidonn devO CиtIC0 TasksPeady To Mergeh tproresoy8 Aeclya AngelovaAssion to meHoporteGalya DimitrovnDevelopmentO Open with VS Code1branch7 commits1 pull request3 buidsRoleases2 See all deploymentsVomiporent| Daily - Platform • nowAll-In-OneCapture AreaCapture Previous AreaCapture FullscreenCapture WindowScrolling Capture• Self-TimerAa Capture Text (OCR)• Record ScreenHide Desktop IconsOpen..Pin to the Screen...Capture History...About CleanShot...Check for Updates...Settings...Quitoeowerviwedecrieated CemicisntaeД л-200в0Setup test coverage forMAINTENANCIDaewrs+₴5+₴3TKTOTRTB100% C8•Fri 15 May 9:46:578colay Yank...Stefka Stoya..0103 others₴8,aliyan Geo...Lukas Kovalik9:46 AM |Daily - Platform...
|
NULL
|
6972701849743824813
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryWindowlahl→Q.C 4 Meet - FirefoxFileEditViewHistoryWindowlahl→Q.C 4 Meet - Daily - Platform+ New TabBookmarksProfilesToolsHelpmeet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting)I7 Sevio0 ProjectsE ANs3 59Platform Team200JY-TS00OJT-S0%v Ready To Be Merged (2 work temwurnwswtewterBasxosД Jy-20678wwrwwwreosnМRIRRTAJ Panorama for Call Scoring in OD~ DescriptionCurrently AJ Panorama in O0 allows managers to get insights about the pertormance of their team. We have now asded afunctionaity for AJ Caili Scoring that aiso provides insights about the performance. It wi be good to leverage both of themIn the chat so that managers can oet the best resuits)• Include the Call Score information for each call in Panorama• the cortext should include - total score, score card name, individual rules score, scoring crteria (the customer'sprompt for the ruie). usttication, timestamp. This information is stored in the ESy Ahachments...-Dute aoded +Screensnol 2040705-15 119.6.42 p0SubtasksAdd subtaskLinked work kemsAoeiedwartem~ ActivityO ar-ososn=0Bacidonn devO CиtIC0 TasksPeady To Mergeh tproresoy8 Aeclya AngelovaAssion to meHoporteGalya DimitrovnDevelopmentO Open with VS Code1branch7 commits1 pull request3 buidsRoleases2 See all deploymentsVomiporent| Daily - Platform • nowAll-In-OneCapture AreaCapture Previous AreaCapture FullscreenCapture WindowScrolling Capture• Self-TimerAa Capture Text (OCR)• Record ScreenHide Desktop IconsOpen..Pin to the Screen...Capture History...About CleanShot...Check for Updates...Settings...Quitoeowerviwedecrieated CemicisntaeД л-200в0Setup test coverage forMAINTENANCIDaewrs+₴5+₴3TKTOTRTB100% C8•Fri 15 May 9:46:578colay Yank...Stefka Stoya..0103 others₴8,aliyan Geo...Lukas Kovalik9:46 AM |Daily - Platform...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46074
|
1649
|
44
|
2026-05-15T06:46:40.524281+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827600524_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
whisper_init_state: kv self size = 3.15 MB
whi whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.
2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)
2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect
2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)
2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)
2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"whisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.\n2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)\n2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)\n2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect\n2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)\n2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)\n2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)\n\n tip: sign in for higher AI quotas + cloud sync:\n screenpipe login","depth":4,"on_screen":true,"value":"whisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.\n2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)\n2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)\n2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect\n2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)\n2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)\n2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)\n\n tip: sign in for higher AI quotas + cloud sync:\n screenpipe login","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
6994266138650324829
|
-815639976654080544
|
app_switch
|
accessibility
|
NULL
|
whisper_init_state: kv self size = 3.15 MB
whi whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.
2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)
2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect
2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)
2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)
2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46072
|
1648
|
28
|
2026-05-15T06:46:39.598038+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827599598_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
whisper_init_state: kv self size = 3.15 MB
whi whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.
2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)
2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect
2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)
2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)
2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"whisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.\n2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)\n2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)\n2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect\n2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)\n2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)\n2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)\n\n tip: sign in for higher AI quotas + cloud sync:\n screenpipe login","depth":4,"on_screen":true,"value":"whisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)\n2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.\n2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)\n2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)\n2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)\n2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect\n2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)\n2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)\n2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)\n\n tip: sign in for higher AI quotas + cloud sync:\n screenpipe login","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
6994266138650324829
|
-815639976654080544
|
app_switch
|
accessibility
|
NULL
|
whisper_init_state: kv self size = 3.15 MB
whi whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:43:04.904386Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:45:06.492820Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:45:35.456345Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:35.521370Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8807740823408271838, trigger=click)
2026-05-15T09:45:44.330889Z WARN screenpipe_audio::core::stream: audio device LakyLak bose qc35 II disconnected. stopping recording.
2026-05-15T09:45:45.308811Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490340Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490468Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)
2026-05-15T09:45:45.490644Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-15T09:45:46.568692Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 216.8ms elapsed (expected 5.3ms) → inserting 211.5ms silence (20301 samples)
2026-05-15T09:45:51.835427Z WARN screenpipe_audio::core::run_record_and_transcribe: no audio received from LakyLak bose qc35 II (input) for 8s - stream dead, triggering reconnect
2026-05-15T09:45:53.214324Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=2592904943322971128, trigger=click)
2026-05-15T09:45:59.186781Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)
2026-05-15T09:46:17.127041Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Idle (timeout, app=Firefox)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46034
|
1649
|
20
|
2026-05-15T06:45:30.492156+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827530492_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
C 80 lbl O l Daily -Platform- now A # 100% €/2 • F C 80 lbl O l Daily -Platform- now A # 100% €/2 • Fri 15 May 9:45:30© github.com/jiminny/app/pull/12077Mlib- scr• NewPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stac XJY-20891 add support for seconda- SRD-6853) Moxso - Potential dea- New TabActivityFllesLateMoreFirefoxVIewMistorbookmarksProtllesToolsWindowmelpJiminny…..Toast# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages88. Stoyan TomovP Galya Dimitrova EP. Aneliya Angelova M€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira CloudToastHomeAboutWeanesday. May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058JY-180911Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolavbiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflicts#11443 lest hubletslatency5 months old • 20 hles+ Aa €17 OpenJY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-changePost findingsSummaryThe PR resets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmbata method and theF1xActiv1t1es0pportun1ty commana.app/Models/Activity-phpLoaic is correct. The reorderina makes sense:if (sthis-»stage id == null dor sstage) (... * 11 fallback still neededThe second if block is still needed — it handles cases where the oooortunitv didn't chanae but stage id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null . Since that branch never changes an existingopportunity, there's no stale stage risk — this asymmetry is intentional and correct.Comment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enough without it — I'd lean toward removing it per the project rules, but it's not a blocker.app/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses Sopportunity->getStageId() - the current stage of the newly matched opportunity, not thestage at the time the activity was originally imported. This is a design decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Settina the stage to the current state of the correct opportunity is the more consistent approach.This seems intentional and correct given the purpose of the command (fixing mismatched opportunities).Potential concern: Opportunity::getStageId() has a non-nullable int return type. If the opportunity somehow has anull stage id in the DB. this would fail at runtime. The command should handle this case aracefullv, e.a, catching theerror or checking for null. That said, if stage_id is always guaranteed non-null for opportunities coming from the CRMmatch this mav he accentahle...
|
NULL
|
-1278541066462599343
|
NULL
|
click
|
ocr
|
NULL
|
C 80 lbl O l Daily -Platform- now A # 100% €/2 • F C 80 lbl O l Daily -Platform- now A # 100% €/2 • Fri 15 May 9:45:30© github.com/jiminny/app/pull/12077Mlib- scr• NewPlatform Sprint 4 Q2 - Platform TeJY-20903 Uodate activity stac XJY-20891 add support for seconda- SRD-6853) Moxso - Potential dea- New TabActivityFllesLateMoreFirefoxVIewMistorbookmarksProtllesToolsWindowmelpJiminny…..Toast# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages88. Stoyan TomovP Galya Dimitrova EP. Aneliya Angelova M€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan Tanev MR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovali.i: AppsG Jira CloudToastHomeAboutWeanesday. May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058JY-180911Update composer tosupport php 8.519 hours old - 260 fileschanged •nikolavbiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 davs old • 12 hlec.changedAdded by Toast for GitHubResolve Conflicts#11443 lest hubletslatency5 months old • 20 hles+ Aa €17 OpenJY-20903 Update activity stage when opportunity is changed #12077LakyLak wants to merge 2 commits into master from JY-20903-update_activity-stage-on-opportunity-changePost findingsSummaryThe PR resets stage_id when the opportunity on an activity changes, to avoid carrying over a stale stage from apreviously matched opportunity. The change is in two places: the model's updateActivityCrmbata method and theF1xActiv1t1es0pportun1ty commana.app/Models/Activity-phpLoaic is correct. The reorderina makes sense:if (sthis-»stage id == null dor sstage) (... * 11 fallback still neededThe second if block is still needed — it handles cases where the oooortunitv didn't chanae but stage id is null.Observation: The same pattern is NOT applied to the UpdateCrmDataByStrategy::Account branch (line 2156), whichonly sets opportunity when Sthis->opportunity_id === null . Since that branch never changes an existingopportunity, there's no stale stage risk — this asymmetry is intentional and correct.Comment (line 2124): Per project convention, comments should only be added for non-obvious quirks. The "why" here(avoiding stale stage) isn't immediately evident from the code alone, so the comment is borderline justified. That said,the code is readable enough without it — I'd lean toward removing it per the project rules, but it's not a blocker.app/Console/Commands/Activities/FixActivities0pportunity.phpResponding to Vasil's question "Activity stage should be the stage at import, no?":The command uses Sopportunity->getStageId() - the current stage of the newly matched opportunity, not thestage at the time the activity was originally imported. This is a design decision:• If the activity had a wrong opportunity (cross-team mismatch), its previous stage was already wrong — restoring"stage at import" of the bad match doesn't help.• Settina the stage to the current state of the correct opportunity is the more consistent approach.This seems intentional and correct given the purpose of the command (fixing mismatched opportunities).Potential concern: Opportunity::getStageId() has a non-nullable int return type. If the opportunity somehow has anull stage id in the DB. this would fail at runtime. The command should handle this case aracefullv, e.a, catching theerror or checking for null. That said, if stage_id is always guaranteed non-null for opportunities coming from the CRMmatch this mav he accentahle...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
46033
|
1648
|
12
|
2026-05-15T06:45:30.473107+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827530473_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelpscreenpipe"₴4<screenpipe*$0885(ah)Daily - Platform - now100% C8• Fri 15 May 9:45:30DOCKERO ₴1DEV (-zsh)82APP (-zsh)*3whisper_init_state:kv crosssize =9.44 MBwhisper_init_state:kv padsize2.36 MBwhisper_init_state:compute buffer (conv)=whisper_init_state:computebuffer (encode) =whisper_init_state:compute buffer (cross)whisper_init_state: computebuffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocatingwhisper_backend_init_gpu:device 0: Metal (type:whisper_backend_init_gpu:found GPU device 0: Metal (type: 1, cnt:0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init:founddevice:Apple M1ggml_metal_init:pickingdefault device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init: use graph optimize=truewhisper_backend_init: using BLAS backendwhisper_init_state: kv selfsize3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state: compute buffer (encode) =whisper_init_state: compute buffer (cross)=whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocatingwhisper_backend_init_gpu: device 0: Metal (type:1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init: found device: Apple M1ggml_metal_init: picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init: use concurrency= trueggml_metal_init: use graph optimize= truewhisper_backend_init: using BLAS backendwhisper_init_state: kv self size=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state: compute buffer (encode) =whisper_init_state: compute buffer (cross)whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15709:45:06.4928202-zshec2-user(INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunksDaily - Platformnow - 09:45-10:05Ci Join Google Meet...
|
NULL
|
-7444224607038828439
|
NULL
|
click
|
ocr
|
NULL
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelpscreenpipe"₴4<screenpipe*$0885(ah)Daily - Platform - now100% C8• Fri 15 May 9:45:30DOCKERO ₴1DEV (-zsh)82APP (-zsh)*3whisper_init_state:kv crosssize =9.44 MBwhisper_init_state:kv padsize2.36 MBwhisper_init_state:compute buffer (conv)=whisper_init_state:computebuffer (encode) =whisper_init_state:compute buffer (cross)whisper_init_state: computebuffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocatingwhisper_backend_init_gpu:device 0: Metal (type:whisper_backend_init_gpu:found GPU device 0: Metal (type: 1, cnt:0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init:founddevice:Apple M1ggml_metal_init:pickingdefault device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init: use graph optimize=truewhisper_backend_init: using BLAS backendwhisper_init_state: kv selfsize3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state: compute buffer (encode) =whisper_init_state: compute buffer (cross)=whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocatingwhisper_backend_init_gpu: device 0: Metal (type:1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init: found device: Apple M1ggml_metal_init: picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init: use concurrency= trueggml_metal_init: use graph optimize= truewhisper_backend_init: using BLAS backendwhisper_init_state: kv self size=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state: compute buffer (encode) =whisper_init_state: compute buffer (cross)whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15709:45:06.4928202-zshec2-user(INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunksDaily - Platformnow - 09:45-10:05Ci Join Google Meet...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45913
|
1647
|
1
|
2026-05-15T06:40:46.173310+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827246173_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLateJiminny ...dtt fiminny-bg# platform-ti ActivityLateJiminny ...dtt fiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-vous# the people of jimi..^ Direct messagesStoyan Tomov• Galva Dimitrova. Aneliya Angelova• Vasil VasilevA. Stefka StoyanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham *Stoyan Tanevea Stelivan Georgievf Petko KashinskiLukas Kovalik y.::AppsS Jira CloudB ToastQ Describe what you are looking forToastHomeMessagesAboutWeanesday, May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-180911Update composer tosupport php 8.519 hours old • 260 flecchangednikolaybiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 Gavs old • 12 HlecchangedAdded by Toast for GitHubResolve Conflictsapp#11443 Test hubletslatency5 months old - 20 fles+ Aa €• Newlib- scre2 scre•• c= DXP4800PLUS-B5F8ClaudoScreenpipe Dashboard@ SQLite Web: archive.db( SQLite Web: db.sgliteWhat's New in Ravcast forNSinance HulNew TabPanerless-nax sian in— New TabScreenpipe• app.screenpipe.lakylak.xyz|XeawnsvS0 hl1Daily - Platform - in 5 m100% C• Fri 15 May 9:40:4513 / 05/ 2026work keportTimetableAl Summary1Acuive «me above = wallclock duration o irecoroine sessions inc uaine uny capsibe weentrames) Apo tocals belowe recordedlrames xys each - these will be lesstinan rac iveltime=code 2n z0miTerm2® browser 4h 3mFirefoxcomms 1h 3mSlack*media 13mQuickTime Plavermother 4h.42mPhpStormWindsurtAlfredCleanShot XAlfred PreferencesMucic@ system 29mFinderKaycastnas.lakvlak.xvz/desktoo/#/nas.lakylak.xyz/desktoo/#/4h 3m1h 3mjiminny.atlassian.net/jira/software/c/prann.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848jiminny.com/tests/packagapp.vanta.com/cvare/c/projects/JY/boards/37/backlogds/37/backloq?selected|ssue=.JY-20676apo.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848...
|
NULL
|
-187095255209473954
|
NULL
|
click
|
ocr
|
NULL
|
ActivityLateJiminny ...dtt fiminny-bg# platform-ti ActivityLateJiminny ...dtt fiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-vous# the people of jimi..^ Direct messagesStoyan Tomov• Galva Dimitrova. Aneliya Angelova• Vasil VasilevA. Stefka StoyanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham *Stoyan Tanevea Stelivan Georgievf Petko KashinskiLukas Kovalik y.::AppsS Jira CloudB ToastQ Describe what you are looking forToastHomeMessagesAboutWeanesday, May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-180911Update composer tosupport php 8.519 hours old • 260 flecchangednikolaybiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 Gavs old • 12 HlecchangedAdded by Toast for GitHubResolve Conflictsapp#11443 Test hubletslatency5 months old - 20 fles+ Aa €• Newlib- scre2 scre•• c= DXP4800PLUS-B5F8ClaudoScreenpipe Dashboard@ SQLite Web: archive.db( SQLite Web: db.sgliteWhat's New in Ravcast forNSinance HulNew TabPanerless-nax sian in— New TabScreenpipe• app.screenpipe.lakylak.xyz|XeawnsvS0 hl1Daily - Platform - in 5 m100% C• Fri 15 May 9:40:4513 / 05/ 2026work keportTimetableAl Summary1Acuive «me above = wallclock duration o irecoroine sessions inc uaine uny capsibe weentrames) Apo tocals belowe recordedlrames xys each - these will be lesstinan rac iveltime=code 2n z0miTerm2® browser 4h 3mFirefoxcomms 1h 3mSlack*media 13mQuickTime Plavermother 4h.42mPhpStormWindsurtAlfredCleanShot XAlfred PreferencesMucic@ system 29mFinderKaycastnas.lakvlak.xvz/desktoo/#/nas.lakylak.xyz/desktoo/#/4h 3m1h 3mjiminny.atlassian.net/jira/software/c/prann.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848jiminny.com/tests/packagapp.vanta.com/cvare/c/projects/JY/boards/37/backlogds/37/backloq?selected|ssue=.JY-20676apo.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848...
|
45910
|
NULL
|
NULL
|
NULL
|
|
45912
|
1646
|
2
|
2026-05-15T06:40:45.777993+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827245777_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksToolsWindowHelp FirefoxFileEditViewHistoryBookmarksToolsWindowHelp‹ >0 lhl• | Daily - Platform • in 5 m100% <7*8• Fri 15 May 9:40:45screenpipe"84181DOCKERO ₴1DEV (-zsh)whisper_init_state:computebufferwhisper_init_state:compute buffer82(cross)(decode) =APP (-zsh)8.50 MB96.83 MB83-zshscreenpipe*885ec2-user@ip-10-20-... *6ec2-user@ip-10-30-...ec2-user@ip-10-...• *8ggml_metal_free: deallocatingwhisper_backend_init_gpu: device 0: Metal (type: 1)whisper_backend_init_gpu: found GPU device 0:Metal (type: 1, cnt: 0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init:use graphoptimizetruewhisper_backend_init:using BLASbackendwhisper_init_state: kv self size3.15MBwhisper_init_state: kv cross size9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)=whisper_init_state: compute buffer(encode) =whisper_init_state: compute buffer (cross)=whisper_init_state: computebuffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15T09:38:59.092116Z2026-05-15T09:40:36.441147ZINFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunksINFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15T09:40:36.474618ZINFOscreenpipe_engine: :event_driven_capture: invalidating persistent streams after unlock/wake for monitor 12026-05-15T09:40:36.479915ZINFO2026-05-15T09:40:36.601895ZINFOsck_rs::stream_manager:stopped 2 persistent stream(s)sck_rs::stream_manager:persistentSCK Stream started for2026-05-15T09:40:36.659780ZWARNdisplay 2 (3008x1253, 2fps, 0 excluded)screenpipe_engine: :event_driven_capture: skipping capture: lock screen app 'loginwindow'on monitor 22026-05-15T09:40:36.767354ZINFOsck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)2026-05-15T09:40:36.814418ZWARNscreenpipe_engine: :event_driven_capture: skipping capture: lock screen app 'loginwindow'on monitor 12026-05-15T09:40:41.444000ZINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15709:40:41.4669852INFOscreenpipe_engine:: event,driven_capture: invalidating persistent streams after unlock/wake for monitor 22026-05-15T09:40:41.496019ZINFOsck_rs::stream_manager:stopped 2 persistent stream(s)2026-05-15T09:40:41.614623ZINFOsck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900,2fps, 0 excluded)2026-05-15709:40:41.7960402INFOsck_rs::stream_manager:persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)2026-05-15T09:40:42.318565ZINFOscreenpipe_audio::core::run_record_and_transcribe: screen unlocked - rebuilding stream for soundcore AeroClip (input) (avoids zombie-callback stateobservedaftersleep/wakeon macOS,Windows,and Linux)2026-05-15T09:40:42.318874ZWARN screenpipe_audio::audio_manager::manager:unlockrecording for device soundcore AeroClip (input) exited with error: stream rebuild required after screenforsoundcoreAeroClip (input)(recoveryisautomatic via device_monitor)2026-05-15T09:40:43.311767ZWARNscreenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stol~nacanding handle for soundcore AeroClip (input), cleaning up forestartFirefox2026-05-15709:40:43.311824Z2026-05-15T09:40:43.408764Z2026-05-15T09:40:43.408810Z2026-05-15T09:40:43.408836ZINFOscreenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (inpue)INFOINFOINFOSCHSCSC$Iput)it) (bluetooth / 30s segments)...
|
NULL
|
-2992957285570176936
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksToolsWindowHelp FirefoxFileEditViewHistoryBookmarksToolsWindowHelp‹ >0 lhl• | Daily - Platform • in 5 m100% <7*8• Fri 15 May 9:40:45screenpipe"84181DOCKERO ₴1DEV (-zsh)whisper_init_state:computebufferwhisper_init_state:compute buffer82(cross)(decode) =APP (-zsh)8.50 MB96.83 MB83-zshscreenpipe*885ec2-user@ip-10-20-... *6ec2-user@ip-10-30-...ec2-user@ip-10-...• *8ggml_metal_free: deallocatingwhisper_backend_init_gpu: device 0: Metal (type: 1)whisper_backend_init_gpu: found GPU device 0:Metal (type: 1, cnt: 0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init:use graphoptimizetruewhisper_backend_init:using BLASbackendwhisper_init_state: kv self size3.15MBwhisper_init_state: kv cross size9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)=whisper_init_state: compute buffer(encode) =whisper_init_state: compute buffer (cross)=whisper_init_state: computebuffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15T09:38:59.092116Z2026-05-15T09:40:36.441147ZINFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunksINFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15T09:40:36.474618ZINFOscreenpipe_engine: :event_driven_capture: invalidating persistent streams after unlock/wake for monitor 12026-05-15T09:40:36.479915ZINFO2026-05-15T09:40:36.601895ZINFOsck_rs::stream_manager:stopped 2 persistent stream(s)sck_rs::stream_manager:persistentSCK Stream started for2026-05-15T09:40:36.659780ZWARNdisplay 2 (3008x1253, 2fps, 0 excluded)screenpipe_engine: :event_driven_capture: skipping capture: lock screen app 'loginwindow'on monitor 22026-05-15T09:40:36.767354ZINFOsck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)2026-05-15T09:40:36.814418ZWARNscreenpipe_engine: :event_driven_capture: skipping capture: lock screen app 'loginwindow'on monitor 12026-05-15T09:40:41.444000ZINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15709:40:41.4669852INFOscreenpipe_engine:: event,driven_capture: invalidating persistent streams after unlock/wake for monitor 22026-05-15T09:40:41.496019ZINFOsck_rs::stream_manager:stopped 2 persistent stream(s)2026-05-15T09:40:41.614623ZINFOsck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900,2fps, 0 excluded)2026-05-15709:40:41.7960402INFOsck_rs::stream_manager:persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)2026-05-15T09:40:42.318565ZINFOscreenpipe_audio::core::run_record_and_transcribe: screen unlocked - rebuilding stream for soundcore AeroClip (input) (avoids zombie-callback stateobservedaftersleep/wakeon macOS,Windows,and Linux)2026-05-15T09:40:42.318874ZWARN screenpipe_audio::audio_manager::manager:unlockrecording for device soundcore AeroClip (input) exited with error: stream rebuild required after screenforsoundcoreAeroClip (input)(recoveryisautomatic via device_monitor)2026-05-15T09:40:43.311767ZWARNscreenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stol~nacanding handle for soundcore AeroClip (input), cleaning up forestartFirefox2026-05-15709:40:43.311824Z2026-05-15T09:40:43.408764Z2026-05-15T09:40:43.408810Z2026-05-15T09:40:43.408836ZINFOscreenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (inpue)INFOINFOINFOSCHSCSC$Iput)it) (bluetooth / 30s segments)...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45911
|
1646
|
1
|
2026-05-15T06:40:42.719901+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827242719_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksToolsWindowHelp FirefoxFileEditViewHistoryBookmarksToolsWindowHelp<| Daily - Platform • in 5m100% C8•Fri 15 May 9:40:42screenpipe"-zsh₴4181DOCKERO ₴1DEV (-zsh)82APP (-zsh)|*3screenpipe"885ec2-user@ip-10-20-...₴6ec2-user@ip-10-30-...ec2-user@ip-10-...• *8whisper_backend_init: usingBLAS backendwhisper_init_state: kv selfsize=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state:computebuffer (encode) =whisper_init_state: compute buffer (cross)whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocatingwhisper_backend_init_gpu: device 0: Metal (type: 1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu:using Metal backendggml_metal_init: allocatingggml_metal_init: found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init: use graph optimize = truewhisper_backend_init: using BLAS backendwhisper_init_state: kv self size3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize2.36 MBwhisper_init_state: compute buffer (conv)=whisper_init_state: compute buffer (encode) =whisper_init_state:compute buffer (cross)whisper_init_state: computebuffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15T09:38:59.092116ZINFO screenpipe_audio::audio_manager::manager: reconciliation:transcribed 50 orphaned chunks2026-05-15T09:40:36.441147ZINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15T09:40:36.474618ZINFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 12026-05-15709:40:36.4799152INFOsck_rs::stream_manager:stopped 2 persistent stream(s)2026-05-15T09:40:36.601895ZINFOsck_rs::stream_manager:persistent SCK stream2026-05-15T09:40:36.659780ZWARNstarted for display 2 (3008x1253, 2fps, 0 excluded)screenpipe_engine::event_driven_capture: skipping capture: lock screen app'loginwindow'on monitor 22026-05-15709:40:36.7673542INFOsck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)2026-05-15T09:40:36.814418ZWARNscreenpipe_engine::event_driven_capture: skipping capture: lock screen app 'loginwindow' on monitor 12026-05-15T09:40:41.444000ZINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15T09:40:41.466985ZINFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 22026-05-15T09:40:41.496019ZINFO sck_rs::stream_manager:stopped 2 persistent stream(s)2026-05-15T09:40:41.614623ZINFOsck_rs::stream_manager:persistent SCKstream started for display 1 (1440x900, 2fps, 0 excluded)2026-05-15T09:40:41.796040ZINFOsck_rs::stream_manager:persistentSCK stream started for display 2 (3008x1253, 2fps, 0 excluded)2026-05-15709:40:42.318565ZINFOscreenpipe_audio::core::run_record_and_transcribe: screen unlocked - rebuilding stream for soundcore AeroClip (input) (avoids zombie-callback stateobservedafter sleep/wake on macOS, Windows,and Linux)2026-05-15T09:40:42.318874ZWARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: stream rebuild required after screenunlock for soundcore AeroClip (input) (recovery is automatic via device_monitor)...
|
NULL
|
8080863097489822208
|
NULL
|
visual_change
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksToolsWindowHelp FirefoxFileEditViewHistoryBookmarksToolsWindowHelp<| Daily - Platform • in 5m100% C8•Fri 15 May 9:40:42screenpipe"-zsh₴4181DOCKERO ₴1DEV (-zsh)82APP (-zsh)|*3screenpipe"885ec2-user@ip-10-20-...₴6ec2-user@ip-10-30-...ec2-user@ip-10-...• *8whisper_backend_init: usingBLAS backendwhisper_init_state: kv selfsize=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state:computebuffer (encode) =whisper_init_state: compute buffer (cross)whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocatingwhisper_backend_init_gpu: device 0: Metal (type: 1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu:using Metal backendggml_metal_init: allocatingggml_metal_init: found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init: use graph optimize = truewhisper_backend_init: using BLAS backendwhisper_init_state: kv self size3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize2.36 MBwhisper_init_state: compute buffer (conv)=whisper_init_state: compute buffer (encode) =whisper_init_state:compute buffer (cross)whisper_init_state: computebuffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15T09:38:59.092116ZINFO screenpipe_audio::audio_manager::manager: reconciliation:transcribed 50 orphaned chunks2026-05-15T09:40:36.441147ZINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15T09:40:36.474618ZINFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 12026-05-15709:40:36.4799152INFOsck_rs::stream_manager:stopped 2 persistent stream(s)2026-05-15T09:40:36.601895ZINFOsck_rs::stream_manager:persistent SCK stream2026-05-15T09:40:36.659780ZWARNstarted for display 2 (3008x1253, 2fps, 0 excluded)screenpipe_engine::event_driven_capture: skipping capture: lock screen app'loginwindow'on monitor 22026-05-15709:40:36.7673542INFOsck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)2026-05-15T09:40:36.814418ZWARNscreenpipe_engine::event_driven_capture: skipping capture: lock screen app 'loginwindow' on monitor 12026-05-15T09:40:41.444000ZINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)2026-05-15T09:40:41.466985ZINFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 22026-05-15T09:40:41.496019ZINFO sck_rs::stream_manager:stopped 2 persistent stream(s)2026-05-15T09:40:41.614623ZINFOsck_rs::stream_manager:persistent SCKstream started for display 1 (1440x900, 2fps, 0 excluded)2026-05-15T09:40:41.796040ZINFOsck_rs::stream_manager:persistentSCK stream started for display 2 (3008x1253, 2fps, 0 excluded)2026-05-15709:40:42.318565ZINFOscreenpipe_audio::core::run_record_and_transcribe: screen unlocked - rebuilding stream for soundcore AeroClip (input) (avoids zombie-callback stateobservedafter sleep/wake on macOS, Windows,and Linux)2026-05-15T09:40:42.318874ZWARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: stream rebuild required after screenunlock for soundcore AeroClip (input) (recovery is automatic via device_monitor)...
|
45909
|
NULL
|
NULL
|
NULL
|
|
45910
|
1647
|
0
|
2026-05-15T06:40:41.496359+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827241496_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ActivityLateJiminny ...dtt fiminny-bg# platform-ti ActivityLateJiminny ...dtt fiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-vous# the people of jimi..^ Direct messagesStoyan Tomov• Galva Dimitrova. Aneliya Angelova• Vasil VasilevA. Stefka StoyanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham *Stoyan Tanevea Stelivan Georgievf Petko KashinskiLukas Kovalik y.::AppsS Jira CloudB ToastQ Describe what you are looking forToastHomeMessagesAboutWeanesday, May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-180911Update composer tosupport php 8.519 hours old • 260 flecchangednikolaybiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 Gavs old • 12 HlecchangedAdded by Toast for GitHubResolve Conflictsapp#11443 Test hubletslatency5 months old - 20 fles+ Aa €• Newlib- scre2 scre•• c= DXP4800PLUS-B5F8ClaudoScreenpipe Dashboard@ SQLite Web: archive.db( SQLite Web: db.sgliteWhat's New in Ravcast forNSinance HulNew TabPanerless-nax sian in— New TabScreenpipe• app.screenpipe.lakylak.xyz|XeawnsvS0 hl1Daily - Platform - in 5 m100% C• Fri 15 May 9:40:4113 / 05/ 2026work keportTimetableAl Summary1Acuive «me above = wallclock duration o irecoroine sessions inc uaine uny capsibe weentrames) Apo tocals belowe recordedlrames xys each - these will be lesstinan rac iveltime=code 2n z0miTerm2® browser 4h 3mFirefoxcomms 1h 3mSlack*media 13mQuickTime Plavermother 4h.42mPhpStormWindsurtAlfredCleanShot XAlfred PreferencesMucic@ system 29mFinderKaycastnas.lakvlak.xvz/desktoo/#/nas.lakylak.xyz/desktoo/#/4h 3m1h 3mjiminny.atlassian.net/jira/software/c/prann.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848jiminny.com/tests/packagapp.vanta.com/cvare/c/projects/JY/boards/37/backlogds/37/backloq?selected|ssue=.JY-20676apo.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848...
|
NULL
|
-808061773265188277
|
NULL
|
app_switch
|
ocr
|
NULL
|
ActivityLateJiminny ...dtt fiminny-bg# platform-ti ActivityLateJiminny ...dtt fiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-vous# the people of jimi..^ Direct messagesStoyan Tomov• Galva Dimitrova. Aneliya Angelova• Vasil VasilevA. Stefka StoyanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanova James Graham *Stoyan Tanevea Stelivan Georgievf Petko KashinskiLukas Kovalik y.::AppsS Jira CloudB ToastQ Describe what you are looking forToastHomeMessagesAboutWeanesday, May 13thapproved by you and @llian KyuchukovYecterdavvToast APP 10:00 AMReview#12058 JY-180911Update composer tosupport php 8.519 hours old • 260 flecchangednikolaybiaivanovAdded bv Toast for GitHubMergeabt#12066 JY-20725 add HSrate limit handling onactivities rematching1 Gavs old • 12 HlecchangedAdded by Toast for GitHubResolve Conflictsapp#11443 Test hubletslatency5 months old - 20 fles+ Aa €• Newlib- scre2 scre•• c= DXP4800PLUS-B5F8ClaudoScreenpipe Dashboard@ SQLite Web: archive.db( SQLite Web: db.sgliteWhat's New in Ravcast forNSinance HulNew TabPanerless-nax sian in— New TabScreenpipe• app.screenpipe.lakylak.xyz|XeawnsvS0 hl1Daily - Platform - in 5 m100% C• Fri 15 May 9:40:4113 / 05/ 2026work keportTimetableAl Summary1Acuive «me above = wallclock duration o irecoroine sessions inc uaine uny capsibe weentrames) Apo tocals belowe recordedlrames xys each - these will be lesstinan rac iveltime=code 2n z0miTerm2® browser 4h 3mFirefoxcomms 1h 3mSlack*media 13mQuickTime Plavermother 4h.42mPhpStormWindsurtAlfredCleanShot XAlfred PreferencesMucic@ system 29mFinderKaycastnas.lakvlak.xvz/desktoo/#/nas.lakylak.xyz/desktoo/#/4h 3m1h 3mjiminny.atlassian.net/jira/software/c/prann.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848jiminny.com/tests/packagapp.vanta.com/cvare/c/projects/JY/boards/37/backlogds/37/backloq?selected|ssue=.JY-20676apo.dev.liminnv.com/dashboardjiminny.atlassian.net/browse/SRD-6848...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45909
|
1646
|
0
|
2026-05-15T06:40:41.467250+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827241467_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
FirefoxFileEditViewHistoryBookmarksToolsWindowHelp FirefoxFileEditViewHistoryBookmarksToolsWindowHelplahl• | Daily - Platform • in 5 mDOCKERO ₴1DEV (-zsh)82ggml_metal_init:allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrencytrueggml_metal_init:use graph optimize =truewhisper_backend_init: using BLAS backendwhisper_init_state: kv self size=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state:compute buffer (conv)whisper_init_state:compute buffer(encode)whisper_init_state:computebuffer (cross)whisper_init_state: compute buffer (decode)ggml_metal_free: deallocatingwhisner hackend init anu: device 0: Metol (tvne: 1)w'APP (-zsh)83-zshscreenpipe"₴4screenpipe"885ec2-user@ip-10-20-... #6100% C8• Fri 15 May 9:40:41181ec2-user@ip-10-30-...ec2-user@ip-10-...• *814.17 MB65.96 MB8.50 MB96.83 MB9$1NFirefoxwhlsper-mee-scuce.whisper_init_state:kv crosssize9.44 MBwhisper_init_state: kv padsize2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state: computebuffer (encode)=whisper_init_state:computebuffer (cross)whisper_init_state:computebuffer (decode) =ggml_metal_free:deallocating2026-05-15709:38:59.09211622026-05-15T09:40:36.441147Z2026-05-15T09:40:36.474618Z2026-05-15T09:40:36.479915Z2026-05-15T09:40:36.601895Z2026-05-15T09:40:36.659780Z2026-05-15T09:40:36.767354Z2026-05-15709:40:36.81441822026-05-15T09:40:41.444000Z2026-05-15T09:40:41.466985Z2026-05-15109:40:41.496019214.17 MB65.96 MB8.50 MB96.83 MBINFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunksINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)INFOscreenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 1INFO sck_rs::stream_manager:stopped 2 persistent stream(s)INFO sck_rs::stream_manager:persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)WARNscreenpipe_engine::event_driven_capture: skipping capture: lock screen app 'loginwindow' on monitor 2INFO sck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900,2fps, 0 excluded)WARN screenpipe_engine::event_driven_capture: skipping capture: lock screen app 'loginwindow' on monitor 1INFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)INFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 2INFO sck_rs::stream_manager:stopped 2 persistent stream(s)...
|
NULL
|
2714837014821262646
|
NULL
|
app_switch
|
ocr
|
NULL
|
FirefoxFileEditViewHistoryBookmarksToolsWindowHelp FirefoxFileEditViewHistoryBookmarksToolsWindowHelplahl• | Daily - Platform • in 5 mDOCKERO ₴1DEV (-zsh)82ggml_metal_init:allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrencytrueggml_metal_init:use graph optimize =truewhisper_backend_init: using BLAS backendwhisper_init_state: kv self size=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state:compute buffer (conv)whisper_init_state:compute buffer(encode)whisper_init_state:computebuffer (cross)whisper_init_state: compute buffer (decode)ggml_metal_free: deallocatingwhisner hackend init anu: device 0: Metol (tvne: 1)w'APP (-zsh)83-zshscreenpipe"₴4screenpipe"885ec2-user@ip-10-20-... #6100% C8• Fri 15 May 9:40:41181ec2-user@ip-10-30-...ec2-user@ip-10-...• *814.17 MB65.96 MB8.50 MB96.83 MB9$1NFirefoxwhlsper-mee-scuce.whisper_init_state:kv crosssize9.44 MBwhisper_init_state: kv padsize2.36 MBwhisper_init_state: compute buffer (conv)whisper_init_state: computebuffer (encode)=whisper_init_state:computebuffer (cross)whisper_init_state:computebuffer (decode) =ggml_metal_free:deallocating2026-05-15709:38:59.09211622026-05-15T09:40:36.441147Z2026-05-15T09:40:36.474618Z2026-05-15T09:40:36.479915Z2026-05-15T09:40:36.601895Z2026-05-15T09:40:36.659780Z2026-05-15T09:40:36.767354Z2026-05-15709:40:36.81441822026-05-15T09:40:41.444000Z2026-05-15T09:40:41.466985Z2026-05-15109:40:41.496019214.17 MB65.96 MB8.50 MB96.83 MBINFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunksINFOscreenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)INFOscreenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 1INFO sck_rs::stream_manager:stopped 2 persistent stream(s)INFO sck_rs::stream_manager:persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)WARNscreenpipe_engine::event_driven_capture: skipping capture: lock screen app 'loginwindow' on monitor 2INFO sck_rs::stream_manager:persistent SCK stream started for display 1 (1440x900,2fps, 0 excluded)WARN screenpipe_engine::event_driven_capture: skipping capture: lock screen app 'loginwindow' on monitor 1INFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)INFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 2INFO sck_rs::stream_manager:stopped 2 persistent stream(s)...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45908
|
NULL
|
0
|
2026-05-15T06:36:40.444662+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778827000444_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
whisper_backend_init: using BLAS backend
whisper_i whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"whisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: wire screenpipe into claude with one command:\n claude mcp add screenpipe -- npx -y screenpipe-mcp\n then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity","depth":4,"on_screen":true,"value":"whisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: wire screenpipe into claude with one command:\n claude mcp add screenpipe -- npx -y screenpipe-mcp\n then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
-6488007505258613009
|
-851668782262979104
|
idle
|
accessibility
|
NULL
|
whisper_backend_init: using BLAS backend
whisper_i whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45902
|
NULL
|
NULL
|
NULL
|
|
45907
|
NULL
|
0
|
2026-05-15T06:36:25.279120+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826985279_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
1420047954182519985
|
-815639976654080544
|
idle
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45905
|
NULL
|
NULL
|
NULL
|
|
45906
|
1645
|
6
|
2026-05-15T06:36:10.218862+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826970218_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
1420047954182519985
|
-815639976654080544
|
idle
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45902
|
NULL
|
NULL
|
NULL
|
|
45905
|
1644
|
6
|
2026-05-15T06:35:55.139695+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826955139_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
1420047954182519985
|
-815639976654080544
|
idle
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45904
|
1645
|
5
|
2026-05-15T06:35:40.028126+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826940028_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
1420047954182519985
|
-815639976654080544
|
idle
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45902
|
NULL
|
NULL
|
NULL
|
|
45903
|
1644
|
5
|
2026-05-15T06:35:25.050580+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826925050_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
1420047954182519985
|
-815639976654080544
|
idle
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45901
|
NULL
|
NULL
|
NULL
|
|
45902
|
1645
|
4
|
2026-05-15T06:35:09.860466+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826909860_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
1420047954182519985
|
-815639976654080544
|
idle
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
screenpipe"
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45901
|
1644
|
4
|
2026-05-15T06:34:54.910089+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826894910_m1.jpg...
|
iTerm2
|
ffmpeg
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
ffmpeg
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
ffmpeg...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ffmpeg","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"ffmpeg","depth":1,"bounds":{"left":0.4826389,"top":0.033333335,"width":0.035416666,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
-1329015425206570765
|
-815639976654080544
|
visual_change
|
accessibility
|
NULL
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames
2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect
2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)
2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:34:54.677866Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
DOCKER
Close Tab
DEV (-zsh)
Close Tab
APP (-zsh)
Close Tab
-zsh
Close Tab
ffmpeg
Close Tab
ec2-user@ip-10-20-31-146:~ (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
ffmpeg...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
45900
|
1645
|
3
|
2026-05-15T06:34:39.672461+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826879672_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
whisper_backend_init: using BLAS backend
whisper_i whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"whisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)","depth":4,"on_screen":true,"value":"whisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
2115983340063954676
|
-852231732216400416
|
idle
|
accessibility
|
NULL
|
whisper_backend_init: using BLAS backend
whisper_i whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45895
|
NULL
|
NULL
|
NULL
|
|
45899
|
1644
|
3
|
2026-05-15T06:34:33.709048+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826873709_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
whisper_backend_init: using BLAS backend
whisper_i whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"whisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)","depth":4,"on_screen":true,"value":"whisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n2026-05-15T09:34:31.090962Z WARN screenpipe_audio::core::run_record_and_transcribe: no usable audio from soundcore AeroClip (input) for 30s — only zero-fill buffers (likely OS device hijack by another app), triggering reconnect\n2026-05-15T09:34:31.093981Z WARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill — no usable data from soundcore AeroClip (input) for 30s (suspected device hijack by another process)\n2026-05-15T09:34:32.062369Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart\n2026-05-15T09:34:32.062583Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177026Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177079Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)\n2026-05-15T09:34:32.177108Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
2115983340063954676
|
-852231732216400416
|
visual_change
|
accessibility
|
NULL
|
whisper_backend_init: using BLAS backend
whisper_i whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45896
|
NULL
|
NULL
|
NULL
|
|
45898
|
1644
|
2
|
2026-05-15T06:34:20.101889+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826860101_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_free: deallocating
whisper_backend_init ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
5134857979507764136
|
-851668773673044512
|
idle
|
accessibility
|
NULL
|
ggml_metal_free: deallocating
whisper_backend_init ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45896
|
NULL
|
NULL
|
NULL
|
|
45897
|
1645
|
2
|
2026-05-15T06:34:09.485257+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826849485_m2.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_free: deallocating
whisper_backend_init ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.27027926,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.27227393,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.32928857,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.33128324,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.3882979,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.39029256,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.44730717,"top":1.0,"width":0.05900931,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.44930187,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.5063165,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.50831115,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.56515956,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.5671542,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.62400264,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.62599736,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.6828458,"top":1.0,"width":0.058843084,"height":-0.042298436},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.68484044,"top":1.0,"width":0.005319149,"height":-0.04549086},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.7280585,"top":1.0,"width":0.01861702,"height":-0.023144484},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.49601063,"top":1.0,"width":0.027925532,"height":-0.02394259},"on_screen":true,"role_description":"text"}]...
|
5134857979507764136
|
-851668773673044512
|
idle
|
accessibility
|
NULL
|
ggml_metal_free: deallocating
whisper_backend_init ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
45895
|
NULL
|
NULL
|
NULL
|
|
45896
|
1644
|
1
|
2026-05-15T06:33:49.975042+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-15/1778 /Users/lukas/.screenpipe/data/data/2026-05-15/1778826829975_m1.jpg...
|
iTerm2
|
screenpipe"
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
ggml_metal_free: deallocating
whisper_backend_init ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
[{"role":"AXTextArea","text [{"role":"AXTextArea","text":"ggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","depth":4,"on_screen":true,"value":"ggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks\n\n tip: get the screenpipe desktop app for the full experience\n https://screenpi.pe\n\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\nwhisper_backend_init_gpu: device 0: Metal (type: 1)\nwhisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)\nwhisper_backend_init_gpu: using Metal backend\nggml_metal_init: allocating\nggml_metal_init: found device: Apple M1\nggml_metal_init: picking default device: Apple M1\nggml_metal_init: use fusion = true\nggml_metal_init: use concurrency = true\nggml_metal_init: use graph optimize = true\nwhisper_backend_init: using BLAS backend\nwhisper_init_state: kv self size = 3.15 MB\nwhisper_init_state: kv cross size = 9.44 MB\nwhisper_init_state: kv pad size = 2.36 MB\nwhisper_init_state: compute buffer (conv) = 14.17 MB\nwhisper_init_state: compute buffer (encode) = 65.96 MB\nwhisper_init_state: compute buffer (cross) = 8.50 MB\nwhisper_init_state: compute buffer (decode) = 96.83 MB\nggml_metal_free: deallocating\n2026-05-15T09:32:52.098771Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 3 eligible frames\n2026-05-15T09:32:52.385067Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks","is_focused":true},{"role":"AXRadioButton","text":"DOCKER","depth":2,"bounds":{"left":0.0,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.004166667,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"DEV (-zsh)","depth":2,"bounds":{"left":0.12326389,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.12743056,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"APP (-zsh)","depth":2,"bounds":{"left":0.24652778,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.25069445,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"-zsh","depth":2,"bounds":{"left":0.36979166,"top":0.05888889,"width":0.12326389,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.37395832,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"screenpipe\"","depth":2,"bounds":{"left":0.49305555,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.49722221,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-20-31-146:~ (-zsh)","depth":2,"bounds":{"left":0.6159722,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.6201389,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-129-190:~ (-zsh)","depth":2,"bounds":{"left":0.73888886,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.7430556,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"ec2-user@ip-10-30-145-148:~ (-zsh)","depth":2,"bounds":{"left":0.86180556,"top":0.05888889,"width":0.12291667,"height":0.026666667},"on_screen":true,"role_description":"radio button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close Tab","depth":3,"bounds":{"left":0.8659722,"top":0.06333333,"width":0.011111111,"height":0.017777778},"on_screen":true,"role_description":"button","is_enabled":false,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"⌥⌘1","depth":1,"bounds":{"left":0.95625,"top":0.032222223,"width":0.03888889,"height":0.018888889},"on_screen":true,"automation_id":"_NS:8","role_description":"text"},{"role":"AXStaticText","text":"screenpipe\"","depth":1,"bounds":{"left":0.47152779,"top":0.033333335,"width":0.058333334,"height":0.017777778},"on_screen":true,"role_description":"text"}]...
|
5134857979507764136
|
-851668773673044512
|
idle
|
accessibility
|
NULL
|
ggml_metal_free: deallocating
whisper_backend_init ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:28:47.974048Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:30:50.199977Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] (-zsh)
Close Tab
ec2-user@ip-10-30-129-190:~ (-zsh)
Close Tab
ec2-user@ip-10-30-145-148:~ (-zsh)
Close Tab
⌥⌘1
screenpipe"...
|
NULL
|
NULL
|
NULL
|
NULL
|