|
45873
|
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:13:25.193120Z 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
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:15:27.572444Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:04.060905Z INFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)
2026-05-14T18:17:04.086797Z INFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 2
2026-05-14T18:17:04.289459Z INFO sck_rs::stream_manager: stopped 2 persistent stream(s)
2026-05-14T18:17:04.514888Z INFO screenpipe_audio::core::run_record_and_transcribe: screen unlocked — rebuilding stream for MacBook Pro Microphone (input) (avoids zombie-callback state observed after sleep/wake on macOS, Windows, and Linux)
2026-05-14T18:17:04.557979Z WARN screenpipe_audio::audio_manager::manager: recording for device MacBook Pro Microphone (input) exited with error: stream rebuild required after screen unlock for MacBook Pro Microphone (input) (recovery is automatic via device_monitor)
2026-05-14T18:17:05.242244Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-14T18:17:05.549376Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for MacBook Pro Microphone (input), cleaning up for restart
2026-05-14T18:17:05.549451Z INFO screenpipe_audio::device::device_manager: Stopping device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.308691Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-14T18:17:06.846677Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.846824Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.846890Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-14T18:17:07.444669Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=374 elapsed=3.00804925s
2026-05-14T18:17:11.045310Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 160.8ms elapsed (expected 5.3ms) → inserting 155.4ms silence (14923 samples)
2026-05-14T18:17:12.775454Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 83.0ms elapsed (expected 5.3ms) → inserting 77.7ms silence (7460 samples)
2026-05-14T18:17:19.588065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-4915557953454808779, trigger=visual_change)
2026-05-14T18:17:19.712429Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4915557953454808779, trigger=visual_change)
2026-05-14T18:17:25.869045Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4915557953454808779, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy →...
|
iTerm2
|
screenpipe"
|
NULL
|
45873
|
|
45874
|
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:13:25.193120Z 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
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:15:27.572444Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:04.060905Z INFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)
2026-05-14T18:17:04.086797Z INFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 2
2026-05-14T18:17:04.289459Z INFO sck_rs::stream_manager: stopped 2 persistent stream(s)
2026-05-14T18:17:04.514888Z INFO screenpipe_audio::core::run_record_and_transcribe: screen unlocked — rebuilding stream for MacBook Pro Microphone (input) (avoids zombie-callback state observed after sleep/wake on macOS, Windows, and Linux)
2026-05-14T18:17:04.557979Z WARN screenpipe_audio::audio_manager::manager: recording for device MacBook Pro Microphone (input) exited with error: stream rebuild required after screen unlock for MacBook Pro Microphone (input) (recovery is automatic via device_monitor)
2026-05-14T18:17:05.242244Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-14T18:17:05.549376Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for MacBook Pro Microphone (input), cleaning up for restart
2026-05-14T18:17:05.549451Z INFO screenpipe_audio::device::device_manager: Stopping device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.308691Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-14T18:17:06.846677Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.846824Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.846890Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-14T18:17:07.444669Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=374 elapsed=3.00804925s
2026-05-14T18:17:11.045310Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 160.8ms elapsed (expected 5.3ms) → inserting 155.4ms silence (14923 samples)
2026-05-14T18:17:12.775454Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 83.0ms elapsed (expected 5.3ms) → inserting 77.7ms silence (7460 samples)
2026-05-14T18:17:19.588065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-4915557953454808779, trigger=visual_change)
2026-05-14T18:17:19.712429Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4915557953454808779, trigger=visual_change)
2026-05-14T18:17:25.869045Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4915557953454808779, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy →...
|
iTerm2
|
screenpipe"
|
NULL
|
45874
|
|
45875
|
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:13:25.193120Z 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
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:15:27.572444Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:04.060905Z INFO screenpipe_engine::sleep_monitor: Screen unlocked (CGSession safety-net poll)
2026-05-14T18:17:04.086797Z INFO screenpipe_engine::event_driven_capture: invalidating persistent streams after unlock/wake for monitor 2
2026-05-14T18:17:04.289459Z INFO sck_rs::stream_manager: stopped 2 persistent stream(s)
2026-05-14T18:17:04.514888Z INFO screenpipe_audio::core::run_record_and_transcribe: screen unlocked — rebuilding stream for MacBook Pro Microphone (input) (avoids zombie-callback state observed after sleep/wake on macOS, Windows, and Linux)
2026-05-14T18:17:04.557979Z WARN screenpipe_audio::audio_manager::manager: recording for device MacBook Pro Microphone (input) exited with error: stream rebuild required after screen unlock for MacBook Pro Microphone (input) (recovery is automatic via device_monitor)
2026-05-14T18:17:05.242244Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-14T18:17:05.549376Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for MacBook Pro Microphone (input), cleaning up for restart
2026-05-14T18:17:05.549451Z INFO screenpipe_audio::device::device_manager: Stopping device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.308691Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-14T18:17:06.846677Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.846824Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: MacBook Pro Microphone (input)
2026-05-14T18:17:06.846890Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-14T18:17:07.444669Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=374 elapsed=3.00804925s
2026-05-14T18:17:11.045310Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 160.8ms elapsed (expected 5.3ms) → inserting 155.4ms silence (14923 samples)
2026-05-14T18:17:12.775454Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 83.0ms elapsed (expected 5.3ms) → inserting 77.7ms silence (7460 samples)
2026-05-14T18:17:19.588065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-4915557953454808779, trigger=visual_change)
2026-05-14T18:17:19.712429Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4915557953454808779, trigger=visual_change)
2026-05-14T18:17:25.869045Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4915557953454808779, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy →...
|
iTerm2
|
screenpipe"
|
NULL
|
45875
|
|
45876
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45876
|
|
45877
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45877
|
|
45878
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45878
|
|
45879
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45879
|
|
45880
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45880
|
|
45881
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45881
|
|
45882
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45882
|
|
45883
|
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
2026-05-14T18:17:32.516386Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 86.0ms elapsed (expected 5.3ms) → inserting 80.7ms silence (7745 samples)
2026-05-14T18:17:32.920163Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:17:41.655714Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=12.584709333s
2026-05-14T18:17:41.659296Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=375 elapsed=1.525763459s
2026-05-14T18:19:15.613896Z WARN sqlx::query: summary="SELECT DISTINCT app_name, window_name, …" db.statement="\n\nSELECT\n DISTINCT app_name,\n window_name,\n browser_url\nFROM\n frames\nWHERE\n timestamp > datetime('now', '-30 seconds')\n AND app_name IS NOT NULL\n AND window_name IS NOT NULL\n" rows_affected=0 rows_returned=383 elapsed=1.089600916s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:19:38.508186Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:19:45.114427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
2026-05-14T18:19:55.429434Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=visual_change)
2026-05-14T18:19:57.285192Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-554583693258477392, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_meta...
|
iTerm2
|
screenpipe"
|
NULL
|
45883
|
|
45885
|
whisper_backend_init_gpu: device 0: Metal (type: 1 whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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_backen...
|
iTerm2
|
screenpipe"
|
NULL
|
45885
|
|
45886
|
whisper_backend_init_gpu: device 0: Metal (type: 1 whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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_backen...
|
iTerm2
|
screenpipe"
|
NULL
|
45886
|
|
45887
|
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
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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 ...
|
iTerm2
|
screenpipe"
|
NULL
|
45887
|
|
45888
|
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
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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 ...
|
iTerm2
|
screenpipe"
|
NULL
|
45888
|
|
45889
|
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
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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 ...
|
iTerm2
|
screenpipe"
|
NULL
|
45889
|
|
45890
|
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
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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 ...
|
iTerm2
|
screenpipe"
|
NULL
|
45890
|
|
45891
|
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
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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 ...
|
iTerm2
|
screenpipe"
|
NULL
|
45891
|
|
45892
|
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
2026-05-14T18:23:45.030577Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:24:19.699073Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 81.3ms elapsed (expected 5.3ms) → inserting 75.9ms silence (7288 samples)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:25:49.236566Z 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
2026-05-14T18:27:52.060944Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=17 elapsed=5.421659208s
2026-05-14T18:27:52.061111Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 17 eligible frames
2026-05-14T18:27:52.632428Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-14T18:27:53.132060Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 9 frames, 1.2MB → 0.6MB (2.2x), 9 JPEGs deleted
2026-05-14T18:27:54.278904Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 8 frames, 1.5MB → 1.1MB (1.4x), 8 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-14T18:29:55.226276Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ alias sp-start
sp-start='npx screenpipe@latest record --disable-audio --ignored-windows "Boosteroid"'
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-15T09:26:34.532591Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-15T09:26:34.611070Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-15T09:26:35.239867Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-15T09:26:35.241531Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-15T09:26:35.241930Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-15T09:26:35.260543Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-15T09:26:35.260623Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-15T09:26:35.632208Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-15T09:26:35.632265Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-15T09:26:35.632219Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-15T09:26:35.632183Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-15T09:26:35.632428Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-15T09:26:35.634456Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-15T09:26:35.634681Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-15T09:26:35.634907Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-15T09:26:35.635461Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-15T09:26:35.635547Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-15T09:26:35.635628Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-15T09:26:35.635643Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
2026-05-15T09:26:35.636459Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ soundcore AeroClip (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-15T09:26:35.637044Z INFO screenpipe: starting UI event capture
2026-05-15T09:26:35.641206Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-15T09:26:35.642634Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-15T09:26:35.650899Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-15T09:26:35.664987Z INFO screenpipe: text-PII worker skipped at startup — async_pii_redaction=false. OPF model (~2.8 GB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665024Z INFO screenpipe: image-PII worker skipped at startup — async_image_pii_redaction=false. rfdetr_v9 model (~108 MB) will NOT be downloaded or loaded. Toggle via Settings → Privacy → AI PII removal.
2026-05-15T09:26:35.665062Z INFO screenpipe_engine::ui_recorder: UI recording session started: af5dd582-4a7c-40c1-a1c7-bc5cff52b88e
2026-05-15T09:26:35.665217Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-14 06:26:35.665214 UTC to 2026-05-15 06:26:35.665214 UTC)
2026-05-15T09:26:35.665146Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-15T09:26:35.666334Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-15T09:26:35.675569Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-15T09:26:35.682913Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-15T09:26:35.796270Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-15T09:26:35.796323Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.796359Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-15T09:26:35.852473Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-15T09:26:35.852505Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-15T09:26:35.852515Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-15T09:26:35.852526Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-15T09:26:35.852543Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-15T09:26:36.408054Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-15T09:26:36.488401Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-15T09:26:36.651362Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=45865, dur=178ms
2026-05-15T09:26:36.658923Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=45866, dur=123ms
2026-05-15T09:26:40.784643Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=7176 elapsed=5.118563458s
2026-05-15T09:26:40.807774Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 7176 frame entries, coverage from 2026-05-14 06:26:35.665214 UTC
2026-05-15T09:26:45.640808Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-15T09:26:45.641039Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-15T09:26:45.641080Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.043 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-15T09:26:45.767408Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T09:26:45.771528Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-15T09:26:45.772132Z INFO screenpipe_audio::audio_manager::manager: seeded 22 speakers (named + unnamed) from DB into embedding manager
2026-05-15T09:26:45.772166Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-15T09:26:45.772179Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-15T09:26:46.236933Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T09:26:46.369731Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-15T09:26:46.369799Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-15T09:26:46.369824Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T09:27:39.547931Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=209 elapsed=3.914452291s
2026-05-15T09:27:39.548108Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 209 eligible frames
2026-05-15T09:27:44.581971Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 84 frames, 19.6MB → 1.4MB (14.3x), 84 JPEGs deleted
2026-05-15T09:27:50.383561Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 99 frames, 18.0MB → 5.1MB (3.5x), 99 JPEGs deleted
2026-05-15T09:27:52.031179Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 4.1MB → 1.0MB (4.1x), 24 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 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 ...
|
iTerm2
|
screenpipe"
|
NULL
|
45892
|
|
45893
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45893
|
|
45894
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45894
|
|
45895
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45895
|
|
45896
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45896
|
|
45897
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45897
|
|
45898
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45898
|
|
45899
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45899
|
|
45900
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45900
|
|
45902
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45902
|
|
45903
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45903
|
|
45904
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45904
|
|
45905
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45905
|
|
45906
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45906
|
|
45907
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45907
|
|
45908
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
45908
|
|
46072
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
46072
|
|
46074
|
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"...
|
iTerm2
|
screenpipe"
|
NULL
|
46074
|
|
46384
|
ActivityLaterMoreJiminny ... ~# jiminny-bg# platfo ActivityLaterMoreJiminny ... ~# jiminny-bg# platform-ticketsic productlaunches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...• Direct messages8. Stoyan TomovP. Galya DimitrovaP. Aneliya Angelova€. Vasil Vasilev8. Stefka Stoyanova DS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham "Ro Stoyan Tanev MR. Steliyan Georgiev =f Petko Kashinski. Lukas Kovalik y...i: Apps® Toast$i Jira CloudQ Describe what you are looking forw releases8 22• Messagesr Filese Bookmarks17599/6e18227kd2h66030eebb36d708a924b12dd)-([URL_WITH_CREDENTIALS] accept_deployvcheckout-code 887480build-frontend 887481test-frontend 887482v build-backend 887483phpstan 887484orevare denlov revision_orod 88/4998build_docker_backend_code_prod 887502build docker worker code prod 8875008 build_docker_worker_video_code_prod 88750db_migrations_prod 8875038 deploy_frontend_assets_to_s3_prod 8875048denlov docker backend code_ orod 887506denlov docker worker code nrod 887505deploy_docker_worker_video_code_prod 8875078sentrv notiiv-1 887508nronaro denlov rovicion nrod eu 8871878build_docker_backend_code_prod_eu 887489All statusesCheckout courcemcp-tools-schemas30252/b Merge branch 'master into mcp-tools-schemasmasteraOOd53b Merge pull request #12073 from jiminny/JY-20891-improve-sms-text-relays E40 ll"Jiminny lech Day • now100% L28• Fri 15 May 10:04:16Trigger eventPush Commit pushedPush Commit pushedStart1m ago4m ago4 Manage triggersnuration59s57s3m 33s1m 12s1m 30s41S1m 19s43sTrigger Pipeline= Display optionsActionsGG.....
|
iTerm2
|
screenpipe"
|
NULL
|
46384
|
|
46385
|
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T09:59:25.294998Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:00:16.744300Z INFO screenpipe_engine::meeting_detector: meeting v2: Active -> Ending (no controls, app=Firefox, id=9, grace=300s)
2026-05-15T10:00:22.419896Z INFO screenpipe_audio::audio_manager::manager: batch mode: audio session ended, transcribing accumulated audio
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:00:25.805165Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
2026-05-15T10:00:35.500672Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8245048993371630268, trigger=visual_change)
2026-05-15T10:00:41.940615Z INFO screenpipe_engine::meeting_detector: meeting v2: Ending -> Active (controls reappeared, app=Firefox, id=9, hysteresis=2/2)
2026-05-15T10:01:14.982726Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:01:28.067481Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
2026-05-15T10:01:54.206890Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:02:03.337683Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:02:06.366420Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:02:12.424846Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:02:15.417860Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:02:33.622277Z INFO screenpipe_engine::meeting_detector: meeting v2: Active -> Ending (no controls, app=Firefox, id=9, grace=300s)
2026-05-15T10:02:41.504330Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 136.8ms elapsed (expected 4.6ms) → inserting 132.2ms silence (12691 samples)
2026-05-15T10:02:50.510031Z INFO screenpipe_audio::audio_manager::manager: batch mode: audio session ended, transcribing accumulated audio
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:02:51.961754Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 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
2026-05-15T10:03:29.780545Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:03:31.131209Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=112 elapsed=2.910282333s
2026-05-15T10:03:31.131509Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 112 eligible frames
2026-05-15T10:03:35.912818Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 71 frames, 12.8MB → 5.5MB (2.3x), 71 JPEGs deleted
2026-05-15T10:03:38.599618Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 39 frames, 6.5MB → 1.9MB (3.5x), 39 JPEGs deleted
2026-05-15T10:03:58.114269Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=click)
2026-05-15T10:04:02.242059Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:16.055543Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 ...
|
iTerm2
|
screenpipe"
|
NULL
|
46385
|
|
46722
|
whisper_init_state: kv cross size = 9.44 MB
whi whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:02:51.961754Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 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
2026-05-15T10:03:29.780545Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:03:31.131209Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=112 elapsed=2.910282333s
2026-05-15T10:03:31.131509Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 112 eligible frames
2026-05-15T10:03:35.912818Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 71 frames, 12.8MB → 5.5MB (2.3x), 71 JPEGs deleted
2026-05-15T10:03:38.599618Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 39 frames, 6.5MB → 1.9MB (3.5x), 39 JPEGs deleted
2026-05-15T10:03:58.114269Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=click)
2026-05-15T10:04:02.242059Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:16.055543Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:45.749136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6964559813879236637, trigger=click)
2026-05-15T10:05:27.172337Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=visual_change)
2026-05-15T10:05:27.510755Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=click)
2026-05-15T10:05:30.812806Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 88.3ms elapsed (expected 5.3ms) → inserting 83.0ms silence (7967 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.079370Z WARN screenpipe_audio::core::stream: audio device soundcore AeroClip disconnected. stopping recording.
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.972705Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:05:33.134587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8471196323029320898, trigger=visual_change)
2026-05-15T10:05:33.295828Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: soundcore AeroClip (input)
2026-05-15T10:05:33.298197Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for MacBook Pro Microphone (input)
2026-05-15T10:05:33.391043Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:05:33.391518Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: soundcore AeroClip (input)
2026-05-15T10:05:33.391563Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
2026-05-15T10:06:34.921783Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:36.545159Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:39.578502Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:42.595977Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:48.684301Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:57.733179Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:00.736489Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:03.787465Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:14.033965Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:26.111577Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:07:33.533196Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:07:35.698235Z INFO screenpipe_engine::meeting_detector: meeting v2: Ending -> Idle (timeout=300s, app=Firefox, id=9)
2026-05-15T10:07:35.875217Z INFO screenpipe_engine::meeting_detector: meeting v2: meeting ended (id=9)
2026-05-15T10:07:35.875613Z INFO screenpipe_engine::routes::meetings: meeting_status_changed: active=false, manual=false, active_id=None, app=None, source=None
2026-05-15T10:07:50.305447Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:56.377587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:02.475230Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:26.625208Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:32.685136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:35.692428Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:40.793299Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=72 elapsed=2.194120875s
2026-05-15T10:08:40.793539Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 72 eligible frames
2026-05-15T10:08:43.904052Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 48 frames, 8.0MB → 2.9MB (2.7x), 48 JPEGs deleted
2026-05-15T10:08:45.460955Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 22 frames, 3.1MB → 0.7MB (4.7x), 22 JPEGs deleted
2026-05-15T10:08:55.698065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:09:35.087072Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:09:47.734757Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:10:13.880551Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:16.919796Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:41.104797Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=179898036855498210, trigger=visual_change)
2026-05-15T10:10:54.258773Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=1154276312842020795, trigger=click)
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:11:37.577060Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:11:46.933038Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:49.145157Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:58.197330Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:13:39.002363Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:13:49.889227Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=84 elapsed=4.427893417s
2026-05-15T10:13:49.889350Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 84 eligible frames
2026-05-15T10:13:52.929679Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 50 frames, 7.8MB → 3.3MB (2.3x), 50 JPEGs deleted
2026-05-15T10:13:55.264589Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 32 frames, 4.9MB → 2.0MB (2.5x), 32 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:15:40.418336Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:16:25.815257Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:16:28.831240Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
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
2026-05-15T10:17:24.077685Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:26.705227Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:27.051451Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:29.707518Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T10:17:41.889109Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:17:42.150435Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:17:44.896908Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:18:55.686978Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 78 eligible frames
2026-05-15T10:18:58.946619Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 47 frames, 8.0MB → 3.7MB (2.2x), 47 JPEGs deleted
2026-05-15T10:19:01.162533Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 29 frames, 4.6MB → 1.5MB (3.0x), 29 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:19:43.534442Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:19:54.454063Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=293848048195837472, trigger=click)
tip: install a starter bundle of pip...
|
iTerm2
|
screenpipe"
|
NULL
|
46722
|
|
46723
|
whisper_init_state: kv cross size = 9.44 MB
whi whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:02:51.961754Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 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
2026-05-15T10:03:29.780545Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:03:31.131209Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=112 elapsed=2.910282333s
2026-05-15T10:03:31.131509Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 112 eligible frames
2026-05-15T10:03:35.912818Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 71 frames, 12.8MB → 5.5MB (2.3x), 71 JPEGs deleted
2026-05-15T10:03:38.599618Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 39 frames, 6.5MB → 1.9MB (3.5x), 39 JPEGs deleted
2026-05-15T10:03:58.114269Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=click)
2026-05-15T10:04:02.242059Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:16.055543Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:45.749136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6964559813879236637, trigger=click)
2026-05-15T10:05:27.172337Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=visual_change)
2026-05-15T10:05:27.510755Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=click)
2026-05-15T10:05:30.812806Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 88.3ms elapsed (expected 5.3ms) → inserting 83.0ms silence (7967 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.079370Z WARN screenpipe_audio::core::stream: audio device soundcore AeroClip disconnected. stopping recording.
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.972705Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:05:33.134587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8471196323029320898, trigger=visual_change)
2026-05-15T10:05:33.295828Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: soundcore AeroClip (input)
2026-05-15T10:05:33.298197Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for MacBook Pro Microphone (input)
2026-05-15T10:05:33.391043Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:05:33.391518Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: soundcore AeroClip (input)
2026-05-15T10:05:33.391563Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
2026-05-15T10:06:34.921783Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:36.545159Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:39.578502Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:42.595977Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:48.684301Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:57.733179Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:00.736489Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:03.787465Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:14.033965Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:26.111577Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:07:33.533196Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:07:35.698235Z INFO screenpipe_engine::meeting_detector: meeting v2: Ending -> Idle (timeout=300s, app=Firefox, id=9)
2026-05-15T10:07:35.875217Z INFO screenpipe_engine::meeting_detector: meeting v2: meeting ended (id=9)
2026-05-15T10:07:35.875613Z INFO screenpipe_engine::routes::meetings: meeting_status_changed: active=false, manual=false, active_id=None, app=None, source=None
2026-05-15T10:07:50.305447Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:56.377587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:02.475230Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:26.625208Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:32.685136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:35.692428Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:40.793299Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=72 elapsed=2.194120875s
2026-05-15T10:08:40.793539Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 72 eligible frames
2026-05-15T10:08:43.904052Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 48 frames, 8.0MB → 2.9MB (2.7x), 48 JPEGs deleted
2026-05-15T10:08:45.460955Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 22 frames, 3.1MB → 0.7MB (4.7x), 22 JPEGs deleted
2026-05-15T10:08:55.698065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:09:35.087072Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:09:47.734757Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:10:13.880551Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:16.919796Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:41.104797Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=179898036855498210, trigger=visual_change)
2026-05-15T10:10:54.258773Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=1154276312842020795, trigger=click)
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:11:37.577060Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:11:46.933038Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:49.145157Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:58.197330Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:13:39.002363Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:13:49.889227Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=84 elapsed=4.427893417s
2026-05-15T10:13:49.889350Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 84 eligible frames
2026-05-15T10:13:52.929679Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 50 frames, 7.8MB → 3.3MB (2.3x), 50 JPEGs deleted
2026-05-15T10:13:55.264589Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 32 frames, 4.9MB → 2.0MB (2.5x), 32 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:15:40.418336Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:16:25.815257Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:16:28.831240Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
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
2026-05-15T10:17:24.077685Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:26.705227Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:27.051451Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:29.707518Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T10:17:41.889109Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:17:42.150435Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:17:44.896908Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:18:55.686978Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 78 eligible frames
2026-05-15T10:18:58.946619Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 47 frames, 8.0MB → 3.7MB (2.2x), 47 JPEGs deleted
2026-05-15T10:19:01.162533Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 29 frames, 4.6MB → 1.5MB (3.0x), 29 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:19:43.534442Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:19:54.454063Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=293848048195837472, trigger=click)
tip: install a starter bundle of pip...
|
iTerm2
|
screenpipe"
|
NULL
|
46723
|
|
46772
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelpla6|Backend Chapter • in 2 mscreenpipe"₴4screenpipe*A100% [8 • Fri 15 May 10:28:49181ec2-user@ip-10-30-...ec2-user@ip-10-...• *8DOCKERO ₴1DEV (-zsh)82APP (-zsh)*3-zsh885ec2-user@ip-10-20-...₴86|ggml_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 optimizetruewhisper_backend_init: using BLAS backendwhisper_init_state: kv selfsize3.15 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: deallocatingwhisper_backend_init_gpu:device 0: Metal (type: 1)whisper_backend_init_gpu:found GPUwhisper_backend_init_gpu:usingdevice 0: Metal (type: 1, cnt:Metal backendggml_metal_init: allocatingggml_metal_init:founddevice: 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 size9.44 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: deallocating2026-05-15T10:27:49.174830ZINFOscreenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks2026-05-15110:28:18.7050192WARNscreenpipe_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 reconnect2026-05-15T10:28:18.705699ZWARN screenpipe_audio::audio_manager::manager: recording for device soundcore AeroClip (input) exited with error: Audio stream zero-fill - no usable data fromsoundcore AeroClip(input)for 30s (suspected device hijack by another process)2026-05-15T10:28:19.916604ZWARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart2026-05-15T10:28:19.916806Z2026-05-15710:28:20.010553Z2026-05-15T10:28:20.010617Z2026-05-15T10:28:20.010644Z2026-05-15110:28:37.4784912INFOscreenpipe_audio::device::device_manager: Stopping device:soundcore AeroClip (input)INFOscreenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)INFOscreenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)INFO screenpipe_audio::core::run_record_and_transcribe: startingcontinuous recordingfor soundcore AeroClip (input) (bluetooth / 30s segments)INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5039982152598914102, trigger=click)...
|
iTerm2
|
screenpipe"
|
NULL
|
46772
|
|
46773
|
FirefoxHomeActivityJiminny ... ~# jiminny-bg# plat FirefoxHomeActivityJiminny ... ~# jiminny-bg# platform-tickets# product launches# random# releases# soha-office# support# thank-yous# the_people_of jimi...• Direct messages8. Stoyan TomovP. Galya Dimitrova. Aneliya Angelova€. Vasil Vasilev8. Stefka StoyanovaS: Todor Stamatov8. Mario Georgiev.. Nikolay Ivanov2o James Graham *Ro Stoyan TanevR. Steliyan Georgiev =. Petko Kashinski. Lukas Kovalik y...i: Apps® ToastG Jira CloudImi Conalo CaleMistorbookmarksProtllesTOOISWindowHelp. Stoyan Tomov• Messagest Add canvasO FilesMoreThursday, April 23rd~A huddle happened 2-26 PMYou and Stoyan Tomov were in the huddlefor 15m.Stoyan Tomov 2:54 PMтова за дайльр разговорите да им сепушват съмаритата винаги важи завсички СRМ-и нали такане е специфично само за 3охоLukas Kovallik 2:54 PMYesterdavvlukas Kovalllk 4.20 pMзппастиработиш ли oшe (edited)Stovan lomov 6.35PM•не но се навъотам покрай компютьваLukas Kovalik 6:36PMутое ше те питам• Saved for later • Due 1 hour agoайле лекаMessage Stoyan Tomov+ Aa €Mlib- scr2 scrPlatform Sprint 4 Q2 - Platform TeService-Desk - Queues - Platfc XJY-20903 Update activity stage wl•JY-20904 Fix UpdateActivityElasJY-20903 Update activity stage wi. JY-20891 add support for seconda…SRD-68531 Moxso - Potential desPipelines - jiminny/appFeed — liminny — Sentry€ [JY-20906] Review of Pipedrive S,p Pipedrive API Reference and Docu@ pipedrive/client-pho: Pipedrive APC< 40 ll O f Backend Chapter-in2m A 100%C4 &• Fri 15 May 10:28:49©jiminny.atlassian.net/jira/servicedesk/projects/SRD/queues/custom/37/SRD-6848O JIMINNYQ Search+ CreateAsk Rov l@ For you© Recent# Starred8$ Apps0, Spaces+...Jiminny (New)Q Service-Desk& Queues- ..•Team Priority|f All open tickets 15@ Unassigned t... 5E Support tea... 5f Raised by me oAssigned to ... 2Ej Service requ... 4I@ Platform team 2Processing t... 10Site reliability... Of New features... OInfoSec issues 0# Ready for Cu... O@ Resolved ti.. 999+= View all queues ># Service requestsA IncidentsHil Reports@ Operations# Knowledge Base& Customers0 Channels.Email logs*> Developer escalationsSlack integration& Reporting Center...
|
iTerm2
|
screenpipe"
|
NULL
|
46773
|
|
46812
|
2026-05-15T10:03:29.780545Z INFO screenpipe_audio 2026-05-15T10:03:29.780545Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:03:31.131209Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=112 elapsed=2.910282333s
2026-05-15T10:03:31.131509Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 112 eligible frames
2026-05-15T10:03:35.912818Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 71 frames, 12.8MB → 5.5MB (2.3x), 71 JPEGs deleted
2026-05-15T10:03:38.599618Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 39 frames, 6.5MB → 1.9MB (3.5x), 39 JPEGs deleted
2026-05-15T10:03:58.114269Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=click)
2026-05-15T10:04:02.242059Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:16.055543Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:45.749136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6964559813879236637, trigger=click)
2026-05-15T10:05:27.172337Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=visual_change)
2026-05-15T10:05:27.510755Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=click)
2026-05-15T10:05:30.812806Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 88.3ms elapsed (expected 5.3ms) → inserting 83.0ms silence (7967 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.079370Z WARN screenpipe_audio::core::stream: audio device soundcore AeroClip disconnected. stopping recording.
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.972705Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:05:33.134587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8471196323029320898, trigger=visual_change)
2026-05-15T10:05:33.295828Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: soundcore AeroClip (input)
2026-05-15T10:05:33.298197Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for MacBook Pro Microphone (input)
2026-05-15T10:05:33.391043Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:05:33.391518Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: soundcore AeroClip (input)
2026-05-15T10:05:33.391563Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
2026-05-15T10:06:34.921783Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:36.545159Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:39.578502Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:42.595977Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:48.684301Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:57.733179Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:00.736489Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:03.787465Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:14.033965Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:26.111577Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:07:33.533196Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:07:35.698235Z INFO screenpipe_engine::meeting_detector: meeting v2: Ending -> Idle (timeout=300s, app=Firefox, id=9)
2026-05-15T10:07:35.875217Z INFO screenpipe_engine::meeting_detector: meeting v2: meeting ended (id=9)
2026-05-15T10:07:35.875613Z INFO screenpipe_engine::routes::meetings: meeting_status_changed: active=false, manual=false, active_id=None, app=None, source=None
2026-05-15T10:07:50.305447Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:56.377587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:02.475230Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:26.625208Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:32.685136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:35.692428Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:40.793299Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=72 elapsed=2.194120875s
2026-05-15T10:08:40.793539Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 72 eligible frames
2026-05-15T10:08:43.904052Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 48 frames, 8.0MB → 2.9MB (2.7x), 48 JPEGs deleted
2026-05-15T10:08:45.460955Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 22 frames, 3.1MB → 0.7MB (4.7x), 22 JPEGs deleted
2026-05-15T10:08:55.698065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:09:35.087072Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:09:47.734757Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:10:13.880551Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:16.919796Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:41.104797Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=179898036855498210, trigger=visual_change)
2026-05-15T10:10:54.258773Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=1154276312842020795, trigger=click)
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:11:37.577060Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:11:46.933038Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:49.145157Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:58.197330Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:13:39.002363Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:13:49.889227Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=84 elapsed=4.427893417s
2026-05-15T10:13:49.889350Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 84 eligible frames
2026-05-15T10:13:52.929679Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 50 frames, 7.8MB → 3.3MB (2.3x), 50 JPEGs deleted
2026-05-15T10:13:55.264589Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 32 frames, 4.9MB → 2.0MB (2.5x), 32 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:15:40.418336Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:16:25.815257Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:16:28.831240Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
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
2026-05-15T10:17:24.077685Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:26.705227Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:27.051451Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:29.707518Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T10:17:41.889109Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:17:42.150435Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:17:44.896908Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:18:55.686978Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 78 eligible frames
2026-05-15T10:18:58.946619Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 47 frames, 8.0MB → 3.7MB (2.2x), 47 JPEGs deleted
2026-05-15T10:19:01.162533Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 29 frames, 4.6MB → 1.5MB (3.0x), 29 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:19:43.534442Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:19:54.454063Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=293848048195837472, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:21:45.045347Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:23:44.091728Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3783661799407507212, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:23:46.406743Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:23:47.100220Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3783661799407507212, trigger=visual_change)
2026-05-15T10:23:50.168615Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3783661799407507212, trigger=visual_change)
2026-05-15T10:23:56.209427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-3131380257679146262, trigger=visual_change)
2026-05-15T10:24:01.598840Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 83 eligible frames
2026-05-15T10:24:03.468500Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 30 frames, 4.0MB → 0.8MB (5.1x), 30 JPEGs deleted
2026-05-15T10:24:06.843609Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 51 frames, 9.5MB → 3.2MB (2.9x), 51 JPEGs deleted
2026-05-15T10:24:14.439978Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7555493398188147089, trigger=visual_change)
2026-05-15T10:25:36.265674Z 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
2026-05-15T10:25:36.265744Z 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)
2026-05-15T10:25:38.212145Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T10:25:38.212421Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T10:25:38.318122Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:25:38.318180Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T10:25:38.318218Z 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
2026-05-15T10:25:47.891816Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free...
|
iTerm2
|
screenpipe"
|
NULL
|
46812
|
|
46813
|
2026-05-15T10:03:29.780545Z INFO screenpipe_audio 2026-05-15T10:03:29.780545Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:03:31.131209Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=112 elapsed=2.910282333s
2026-05-15T10:03:31.131509Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 112 eligible frames
2026-05-15T10:03:35.912818Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 71 frames, 12.8MB → 5.5MB (2.3x), 71 JPEGs deleted
2026-05-15T10:03:38.599618Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 39 frames, 6.5MB → 1.9MB (3.5x), 39 JPEGs deleted
2026-05-15T10:03:58.114269Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=click)
2026-05-15T10:04:02.242059Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:16.055543Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7514941666263664050, trigger=visual_change)
2026-05-15T10:04:45.749136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6964559813879236637, trigger=click)
2026-05-15T10:05:27.172337Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=visual_change)
2026-05-15T10:05:27.510755Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6968430965336078127, trigger=click)
2026-05-15T10:05:30.812806Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 88.3ms elapsed (expected 5.3ms) → inserting 83.0ms silence (7967 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.079370Z WARN screenpipe_audio::core::stream: audio device soundcore AeroClip disconnected. stopping recording.
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:05:31.972705Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:05:33.134587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8471196323029320898, trigger=visual_change)
2026-05-15T10:05:33.295828Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: soundcore AeroClip (input)
2026-05-15T10:05:33.298197Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for MacBook Pro Microphone (input)
2026-05-15T10:05:33.391043Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:05:33.391518Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: soundcore AeroClip (input)
2026-05-15T10:05:33.391563Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
2026-05-15T10:06:34.921783Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:36.545159Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:39.578502Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:42.595977Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:48.684301Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:06:57.733179Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:00.736489Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:03.787465Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8592070119316887513, trigger=visual_change)
2026-05-15T10:07:14.033965Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:26.111577Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:07:33.533196Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:07:35.698235Z INFO screenpipe_engine::meeting_detector: meeting v2: Ending -> Idle (timeout=300s, app=Firefox, id=9)
2026-05-15T10:07:35.875217Z INFO screenpipe_engine::meeting_detector: meeting v2: meeting ended (id=9)
2026-05-15T10:07:35.875613Z INFO screenpipe_engine::routes::meetings: meeting_status_changed: active=false, manual=false, active_id=None, app=None, source=None
2026-05-15T10:07:50.305447Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:07:56.377587Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:02.475230Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:26.625208Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:32.685136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:35.692428Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:08:40.793299Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=72 elapsed=2.194120875s
2026-05-15T10:08:40.793539Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 72 eligible frames
2026-05-15T10:08:43.904052Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 48 frames, 8.0MB → 2.9MB (2.7x), 48 JPEGs deleted
2026-05-15T10:08:45.460955Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 22 frames, 3.1MB → 0.7MB (4.7x), 22 JPEGs deleted
2026-05-15T10:08:55.698065Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:09:35.087072Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:09:47.734757Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7118676075647864272, trigger=visual_change)
2026-05-15T10:10:13.880551Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:16.919796Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6670048487670008310, trigger=visual_change)
2026-05-15T10:10:41.104797Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=179898036855498210, trigger=visual_change)
2026-05-15T10:10:54.258773Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=1154276312842020795, trigger=click)
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:11:37.577060Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:11:46.933038Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:49.145157Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
2026-05-15T10:11:58.197330Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6120817221547753544, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:13:39.002363Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:13:49.889227Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=84 elapsed=4.427893417s
2026-05-15T10:13:49.889350Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 84 eligible frames
2026-05-15T10:13:52.929679Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 50 frames, 7.8MB → 3.3MB (2.3x), 50 JPEGs deleted
2026-05-15T10:13:55.264589Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 32 frames, 4.9MB → 2.0MB (2.5x), 32 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:15:40.418336Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:16:25.815257Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:16:28.831240Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
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
2026-05-15T10:17:24.077685Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:26.705227Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:27.051451Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:17:29.707518Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-15T10:17:41.889109Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:17:42.150435Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:17:44.896908Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5229934648328219625, trigger=visual_change)
2026-05-15T10:18:55.686978Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 78 eligible frames
2026-05-15T10:18:58.946619Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 47 frames, 8.0MB → 3.7MB (2.2x), 47 JPEGs deleted
2026-05-15T10:19:01.162533Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 29 frames, 4.6MB → 1.5MB (3.0x), 29 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:19:43.534442Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:19:54.454063Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=293848048195837472, trigger=click)
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:21:45.045347Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:23:44.091728Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3783661799407507212, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:23:46.406743Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:23:47.100220Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3783661799407507212, trigger=visual_change)
2026-05-15T10:23:50.168615Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3783661799407507212, trigger=visual_change)
2026-05-15T10:23:56.209427Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-3131380257679146262, trigger=visual_change)
2026-05-15T10:24:01.598840Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 83 eligible frames
2026-05-15T10:24:03.468500Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 30 frames, 4.0MB → 0.8MB (5.1x), 30 JPEGs deleted
2026-05-15T10:24:06.843609Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 51 frames, 9.5MB → 3.2MB (2.9x), 51 JPEGs deleted
2026-05-15T10:24:14.439978Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7555493398188147089, trigger=visual_change)
2026-05-15T10:25:36.265674Z 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
2026-05-15T10:25:36.265744Z 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)
2026-05-15T10:25:38.212145Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T10:25:38.212421Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T10:25:38.318122Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:25:38.318180Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T10:25:38.318218Z 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
2026-05-15T10:25:47.891816Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free...
|
iTerm2
|
screenpipe"
|
NULL
|
46813
|
|
47121
|
FinderFileEditViewGoWindowHelplab|Backend Chapter FinderFileEditViewGoWindowHelplab|Backend Chapter • 35 m leftБГ100% [Fri 15 May 10:55:56DOCKERO ₴1DEV (-zsh)82APP (-zsh)*3whisper_backend_init_gpu: device 0: Metal(type:1)whisper_backend_init_gpu: found GPUdevice 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: 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 optimizetruewhisper_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: computebuffer (encode) =whisper_init_state: computebuffer (cross)whisper_init_state: compute buffer (decode) =14.17 MB65.96 MB8.50 MB96.83 MBggml_metal_free: deallocating2026-05-15T10:54:39.377575Z2026-05-15T10:55:04.696096ZROM\nframes \nWHERE\n895125s2026-05-15710:55:04.69624222026-05-15T10:55:06.875955Z2026-05-15T10:55:07.81309122026-05-15110:55:48.2135682-zshscreenpipe"₴4181screenpipe*885ec2-user@ip-10-20-...₴86|ec2-user@ip-10-30-...ec2-user@ip-10-...• *8INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunksWARN sqlx::query:summary-"SELECT id, snapshot_path, device_name, -"db.statement="\n\nSELECT\n id,\nsnapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name, \ntimestamp ASC\nLIMIT\n5000\n'snapshot_path,\ndevice_name, \ntimestamp\nFrows_affected=0 rows_returned=49elapsed=2.487INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 49 eligible framesINFO screenpipe_engine::snapshot_compaction: snapshot compaction: 33 frames, 5.7MB → 1.9MB (3.0x), 33 JPEGs deletedINFO screenpipe_engine::snapshot_compaction: snapshot compaction: 14 frames,2.1MB → 0.3MB (7.0x), 14 JPEGs deletedINFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8751488911070003529, trigger=visual_change)...
|
iTerm2
|
screenpipe"
|
NULL
|
47121
|
|
47122
|
ActivityACUIVILy MonitorJiminny ... ~# jiminny-bg# ActivityACUIVILy MonitorJiminny ... ~# jiminny-bg# platform-ticketsic productlaunches# random# releases# soha-office# support# thank-vous# the people of jimi..ó- Direct messagesStoyan Tomov• Galva Dimitrova. Aneliya Angelova• Vasil Vasilevn Stefka StoyanovaSe: Todor StamatovNa Mario GeorgievNikolay Ivanov. James Graham "o Stoyan Tanevd Stelivan Georgievf Petko KashinskiLukas Kovalik y...::: AppsToastSi Jira GloudViewWindownelpDescribe wnat you are lookins folStoyan Tomov• Messagest Add canvas( FilesMorevOpen in dire*Summariseфикс прелставлява лобавяне наsecondarv emailза ла може ла се намери userлеплойнах промените вечеreally sorry but we could not send your text molten que to the message being too long)To e genericне сьм разбрал дали в крайна сметка тисм Марио сьщо го получихтев база вашите не са failedStovan lomov 10:37 AMIсложих му на юзь02 втовия мейл онзи.Иначе съобщението че SMS не е пратени аз и марио го получихме като отговорв пошата выплеки че sms-ите сe бяхаизпоатилиMessage Stoyan Tomov+ Aa Iv Q SearchGrouplibscreenpipe_revert_db.shscreenpipe_sync.shActionAutrocy MonitorProcess NameWindowServerkernel_taskFirefoxCP Isolated Web Content•FirefoxCP Isolated Web ContentcoreaudiodFirefoxcP Isolated Web ContentFirefo»iTerm2Slack Heloer (Renderer)bluetoothcSlackAddressBookSourceSyncWispr Flow Helper (Renderer)trustelaunchdW Wisor FlowassistantaClaudeFindeneanwtthtewhenrunninaboarddfseventsdio.kandii.KandiiAgent.ESF.FxtensionWispr Flow Helper (Renderer)Wisor Flow Heloer (GPU)Karabiner-Core-Service2 Control CentreCPU Memoryidle Wake-Ups% CPU69,133.830,918,814,914,313.310,8Cpu TimeThreads6:35:52,4110:47:51,7227:14:54,951:15,5720,5017:15.511,584:35,6730:39,822:11:07,7342,55111643:11,172:17:28,331:41:01.7734:05,9226:32,785:18,790.4852:18,515:03,4543:43,771:12:45.7512.8831:04.14148:31,3939:45.8523:39,262:35:58.840,575:11.8313:10,4440:49,531:14:33,9522:51.690,5956.2912:52,0048:02.1018:16,9541,061,0641:49.5535:20.47System21790GeAnoAppleAppleAppleAppieAppleAppleAppleAppleAppleAppleAppleAnoleAppleAnoleAppleAppleAppleAnoleAppleAnoleAppleAppleAnoleAppleApoleAppleApoleAppleApoleAppleApoleApoleS0 hll% GPUeo ltuime64.44:55:49.800.000,00,000.580,000,00|0,000.000.0310,520.000,[IP_ADDRESS].000.000.00|0.000.000.3810,000.000,000.000,003.770.001:30,570.000.000.00Threads:Backend Chapter • 35 m left100% 152Fri 15 May 10:55: gлgen33577943375839994772|rootlukaslukaslukaslukaslukaslukasllukaslukaslukasroot3956...
|
iTerm2
|
screenpipe"
|
NULL
|
47122
|
|
47123
|
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
2026-05-15T10:29:50.596455Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:30:25.482831Z 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
2026-05-15T10:30:25.483120Z 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)
2026-05-15T10:30:25.571378Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T10:30:25.571515Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T10:30:25.691055Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:30:25.691096Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T10:30:25.691124Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-15T10:31:05.636050Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=681556466160362218, trigger=click)
2026-05-15T10:31:05.640455Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=681556466160362218, trigger=click)
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:31:52.172233Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:33:37.537667Z 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
2026-05-15T10:33:37.538078Z 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)
2026-05-15T10:33:38.294226Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] detected stale recording handle for soundcore AeroClip (input), cleaning up for restart
2026-05-15T10:33:38.294389Z INFO screenpipe_audio::device::device_manager: Stopping device: soundcore AeroClip (input)
2026-05-15T10:33:38.428874Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-15T10:33:38.428965Z INFO screenpipe_audio::audio_manager::device_monitor: restarted with system default device: soundcore AeroClip (input)
2026-05-15T10:33:38.429012Z 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
2026-05-15T10:33:54.009302Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:33:57.063839Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-4900808485845100823, trigger=click)
2026-05-15T10:34:16.747788Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=118 elapsed=1.479713s
2026-05-15T10:34:16.748140Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 118 eligible frames
2026-05-15T10:34:19.257702Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 41 frames, 8.6MB → 0.4MB (19.4x), 41 JPEGs deleted
2026-05-15T10:34:22.149737Z INFO screenpipe_engine::meeting_detector: meeting v2: Idle -> Confirming (app=Firefox, signals=2)
2026-05-15T10:34:28.038868Z INFO screenpipe_engine::meeting_detector: meeting v2: Confirming -> Active (app=Firefox, signals=2, browser=true)
2026-05-15T10:34:28.089970Z INFO screenpipe_engine::meeting_detector: meeting v2: meeting started (id=10, app=Firefox, title=None)
2026-05-15T10:34:28.092786Z INFO screenpipe_engine::routes::meetings: meeting_status_changed: active=true, manual=false, active_id=Some(10), app=Some("Firefox"), source=Some("ui_scan")
2026-05-15T10:34:29.853277Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 75 frames, 12.1MB → 3.8MB (3.2x), 75 JPEGs deleted
2026-05-15T10:34:35.822637Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1548446519404518590, trigger=visual_change)
2026-05-15T10:35:25.074806Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=928002058639081556, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:35:57.381952Z 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
2026-05-15T10:36:38.222462Z INFO screenpipe_engine::meeting_detector: meeting v2: Active -> Ending (no controls, app=Firefox, id=10, grace=300s)
2026-05-15T10:36:40.125458Z INFO screenpipe_audio::audio_manager::manager: batch mode: audio session ended, transcribing accumulated audio
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:36:42.784622Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
2026-05-15T10:36:58.406181Z INFO screenpipe_engine::meeting_detector: meeting v2: Ending -> Active (controls reappeared, app=Firefox, id=10, hysteresis=2/2)
2026-05-15T10:37:16.344488Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8491420810700273995, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:38:00.234315Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:39:32.155158Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=3272837198397708733, trigger=visual_change)
2026-05-15T10:39:33.097579Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=91 elapsed=3.235941417s
2026-05-15T10:39:33.098079Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 91 eligible frames
2026-05-15T10:39:36.038716Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 38 frames, 7.4MB → 2.7MB (2.8x), 38 JPEGs deleted
2026-05-15T10:39:41.039065Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 51 frames, 7.7MB → 2.3MB (3.3x), 51 JPEGs deleted
2026-05-15T10:39:58.029100Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-4003856554507403314, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:40:02.625015Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:40:10.188377Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1181140310473185487, trigger=visual_change)
2026-05-15T10:40:12.097658Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1181140310473185487, trigger=click)
2026-05-15T10:40:46.008567Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-5336120778450163088, trigger=click)
2026-05-15T10:40:58.759980Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-2163510695520779287, trigger=visual_change)
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
2026-05-15T10:41:46.193657Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-3333983279453255371, trigger=visual_change)
2026-05-15T10:41:52.223067Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-3333983279453255371, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:42:05.268233Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:43:13.529033Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-683618393787098226, trigger=visual_change)
2026-05-15T10:43:44.253992Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=5038384051518172246, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:44:07.388155Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:44:11.297850Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:14.354943Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:17.385265Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:23.381558Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:26.392583Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:29.445081Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:32.434017Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7712089156721010816, trigger=visual_change)
2026-05-15T10:44:41.258376Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 83 eligible frames
2026-05-15T10:44:46.255551Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 42 frames, 6.8MB → 2.7MB (2.5x), 42 JPEGs deleted
2026-05-15T10:44:47.607383Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-6468899787655697376, trigger=visual_change)
2026-05-15T10:44:50.467799Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 39 frames, 6.5MB → 1.9MB (3.4x), 39 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:46:09.837193Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
2026-05-15T10:47:11.305818Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:47:14.273613Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:47:17.351792Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:47:20.320752Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:47:26.377483Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:47:29.423178Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:47:38.642923Z INFO screenpipe_audio::audio_manager::manager: batch mode: deferral cap (600s) reached during active session, force-transcribing
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:47:41.015068Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 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
2026-05-15T10:48:11.951590Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:48:27.197512Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=6837736361750022568, trigger=visual_change)
2026-05-15T10:48:40.111059Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8756556117104328980, trigger=visual_change)
2026-05-15T10:48:43.070991Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=8756556117104328980, trigger=visual_change)
2026-05-15T10:48:55.287863Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7038874014184083431, trigger=visual_change)
2026-05-15T10:49:26.399648Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=2413662396953587444, trigger=visual_change)
2026-05-15T10:49:34.435994Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=5112899069431255409, trigger=click)
2026-05-15T10:49:44.530070Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=1582849516488658548, trigger=visual_change)
2026-05-15T10:49:47.575515Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=1582849516488658548, trigger=visual_change)
2026-05-15T10:49:51.558913Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=90 elapsed=1.078157s
2026-05-15T10:49:51.559067Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 90 eligible frames
2026-05-15T10:49:56.691954Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=1582849516488658548, trigger=visual_change)
2026-05-15T10:49:59.754359Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=1582849516488658548, trigger=visual_change)
2026-05-15T10:49:59.958041Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 66 frames, 12.3MB → 5.4MB (2.3x), 66 JPEGs deleted
2026-05-15T10:50:02.195126Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 22 frames, 3.5MB → 0.9MB (3.9x), 22 JPEGs deleted
2026-05-15T10:50:08.791562Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-668400184958936367, trigger=visual_change)
2026-05-15T10:50:11.823815Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-668400184958936367, trigger=visual_change)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-15T10:50:14.042757Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-15T10:50:23.925098Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-668400184958936367, trigger=visual_change)
2026-05-15T10:50:26.917391Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-668400184958936367, trigger=visual_change)
2026-05-15T10:50:33.005285Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-668400184958936367, trigger=visual_change)
2026-05-15T10:50:35.986332Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-668400184958936367, trigger=visual_change)
2026-05-15T10:50:54.169356Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=34795420094709164, trigger=visual_change)
2026-05-15T10:50:57.208417Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=34795420094709164, trigger=visual_change)
2026-05-15T10:51:09.312097Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1035378988443331474, trigger=visual_change)
2026-05-15T10:51:12.347272Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1035378988443331474, trigger=visual_change)
2026-05-15T10:51:18.391181Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1035378988443331474, trigger=visual_change)
2026-05-15T10:51:21.348732Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1035378988443331474, trigger=visual_change)
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
2026-05-15T10:51:48.699475Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-7971876004363886841, trigger=visual_change)
whisper_backend_init_g...
|
iTerm2
|
screenpipe"
|
NULL
|
47123
|
|
47814
|
PhpStormFileEditViewNavigateCodeLaravelRefactorRun PhpStormFileEditViewNavigateCodeLaravelRefactorRunToolsGitWindowHelpscreenpipe"₴4(iho]Jiminny Tech Day • 6h 6 m leftADOCKERO ₴1DEV (-zsh)82APP (-zsh)*3-zshscreenpipe*885ec2-user@ip-10-20-...886-ec2-user@ip-10-30-...whisper_init_state:whisper_init_state:kv padsize2.36 MBcompute 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 optimizetruewhisper_backend_init: usingBLAS backendwhisper_init_state: kv self size3.15 MBwhisper_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: 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 GPUdevice 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 concurrencytrueggml_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 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: deallocating2026-05-15T11:53:17.637552ZINFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks2026-05-15T11:54:01.6843202INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=8724424516320409755, trigger=click)100% [8•Fri 15 May 11:54:03181ec2-user@ip-10-...• *8...
|
iTerm2
|
screenpipe"
|
NULL
|
47814
|
|
47815
|
ActivitFllesPhpStormViewINavicareCodeLaravelKeract ActivitFllesPhpStormViewINavicareCodeLaravelKeractorloolsWindowmelpJiminny...vXstarred• jiminny-x-integrati..8 platform-inner-teamE) Channelsic al-chaoter# alerts# backend# bugs# confusion-clinic# curiosity_lab# engineering# general#jiminny-bg# platform-tickets# product_launches# random# releases# sofa-office# support# thank-yous# the people of fimi..o- Direct messagesStovan Tomov• Galva Dimitrova De Aneliva Angelovaa Vasil VasilevFV faVsco.js?9 JY-20891-improve-sms-text-relays k#reMessagProjectv© InviteUserToTeamAction.php(c) CrmActivityService.ongM+ WEBHOOK FILTERING MPLEMENTATIспескалокешукеmоtемatch.php@ RematchActivityOnCrmObjectDetach.phpih External Liorariesv = Scratches and Consoles•Cird•DerProlag;MessagAa• Database ConsolesVAEU« console [EU]A DEAL RISKS (EU]A DI (EU]A EU (EU]v A jiminny@localhostA console [jiminny@localhost& Ul Uiminny@localnostA no local liminny alocalnostA SF [iiminny@localhost)A zoho dev [jiminny@localhost]• & PRODconsole PROD& console 1 [PROD]& DIIPROD.DLФA> ₫OAiV APA PROD¿ console PA PRODI© Activity.php x| © UpdateCrmData.phpclass Activity extends Model implementsoublic tunction uodate ctvrvermbatalarrav srecords): vo1di64 A169 ×4 ×102 14 ^ V 648212312124212721312133¿ console 1IPA PRODIIA console 2 PA PRODI console 3 leA PROD215521362137I console 4 l0AI PRODd console 5 laAI PRODIIA console 6 loAI PRODIA console 7 lGAI PRODIIASTAGING#concole [STAGING121592140214121492143A concole 1 ICTACINGI& uranus [STAGINGI>D Extensionsv MScratchesEphpstorm_shortcuts.txt3 ccratch tytt scratch_1.jsonccratch 2,isonf° scratch 3.isonscratch_4 txtpig scratch_5.php09 scratch_6.phpf" scratch._7.isonf" scratch_8.ison4° stage2.isonE° test<° test.htmllphe tmo.oho21492146215112152|2157|2154if (this->stage 1d === null && Sstage) <$this->stage_id = $stage->id;if (Sopportunity && Sthis->opportunity_id |== $opportunity->id) {$this->opportunity_id = Sopportunity->id;if (Sopportunity && Sthis->value !== Sopportunity->value) {— 050— 657658659sunis->value = sopporcunity-›value— 661662|// Always set contact id when available, regardless of account id statusif (Sthis->contact id === null && Scontact) {Sthis->contact id = Scontact->id:=667othas->saveo} elseif ($strategy == UpdateCrmDataByStrategy::Account && $this->account_id = 676Also uodate the parent activity if reauired.checking we don't creates$this->lead_id = null;if (Sthis->stage && Sthis->stage-›qetTvne() === Stage::TYPE LEAD) {sthis->stage 1d = nullI undate the account and onnontunito on the setivito necond ie enceibl eSthis->account id= Saccount->id.if (Sthis->stage_id === null && $stage) {Sthis->staae id = Sstage->id»=678E679=680681684if ($this->opportunity id === null && Sopportunity) {$this->opportunity id = Sopportunity->id;c+hic->value = Sooportunity->value,=684 vSthis->saveO:Choskod aut IV.20901.imnravo-eme.tovt-rolaue /22 minutoc snd=custom.logt scratch_8.json= laravel.log4 SF jiminny@localhost]4 HS_local [jiminny@localhost]A console [PROD] X A console [EU]fiò accounts [EU]tii stages (EU]iiò teams ([EU]ImporbotkecoraingJoo.onp© FixActivitiesOpportunity.php• console_/ QAI PRODA console [STAGING)Tx: Autodo jiminnyroul accounts wuere coi cont tuuragont oo a 1y0000040 A1 A40 M65 A Vrom automated_report_results where id = 1976;rom automated_reports where id = 583;rom activity_searches where id = 87714;rom activity_search_filters where activity_search_id = 87714;ROM activities WHERE uuid_to_bin('8827f672-202d-4162-9d04-73ff5f0566a9') = uuid_bin('47842446-af51-4bcb-854f-cc6560290101') = uuid;ROM crm_configurations WHERE provider = 'hubspot';ron race_timits,automated report results where media type = 'pdf' and status = 218, 1812)1where 1d = 54;ROM users WHERE id IN (24623,29443,29613):ROM automated report results WHERE uuid to bin('822fa41b-afd3-43a9-a248-86b0e36f3131') = uuid:|rom text relavs where created at > "2026-05-01°(32415. 32416)324121rom users where team id = 2 and email like '%scottg' and id = 29510:RoM activities WhERE uuld to bin67cehfc2-ed56-4422-8668-1a0286ed8618") = Uuid: # 19163456oroviden id. COUNT*) as count. GROUP CONCATGid as ids. GROUP CONCATistatus) as statusesrelaysIl oroviden id TN119e2027868a64h421119e2033ed8ea6b10')|mail nnoviden id.ctatuc telenhonv nnoviden id copated atitiesIN (RA029710 RAADRRLA)•status, code, email sent at, created at, updated atnplaySN (32415, 32416):code, sender, recipient, created atrelayser LIKE '%mario.georgiev%' OR sender LIKE '%stovan.tomov%rearedar Uesu• Jiminny lech Day • on om len100% 2• Fri 15 May 11:54:03AskJiminnyReview PR tor ActivityDebug Text Relay Fal+0...could you veriry the exact emall they receivea: soecirically:1. Does the emall rerea text relay ID it should say "quoting reterence ia and code{code}")?<. What code is mentioned in the emall:3. Is it definitely the "We're really sorry but we could not send your text message" email, orcould it be a different notification?This will helo determine it they received the SmsRelavsalled email or a ditterent notiication withisimilar wordingFrom: The Jiminny Team <[EMAIL]>Subie wt: do ur ty x3, esza ge failed to sendH6stoyan.tomovejiminny.comswere oaly duey butwmessia n otein doo ur tex message.Peooogast unpo de 20 hfrmatin, qutig oftrne 06281416 2738- 4a8e ate-Thought for 1clPerfect! The email shows:• Reference: 0626141c-27a6-4d8c-af48_7c8020a2c656• Code: 2200Code 2200 is REASON CODE SENDER MISMATCH line 35 in EmailTextRelav.oho), which means"Sender does not match the origin activity."This is a different text_relay record than the one we've been looking at (32416 has UUID 0x4CD18652A4D7AA2DA5268705E3B21366 . Let me tind the record with UUID 0626141c-27a6-4d8c-aff8-7c80• saSELECT id, uuid, status, code, sender, recipient, created at, updated atFROM text relaysWHERE uuid = uuid to bin('0626141c-27a6-4d8c-aff8-7c8020a2c656'):This will show the actual failed text relay record that triggered the failure email Stoyan received.nl "Your included weekly usage quota is exhausted. Using your extra usage. Quota resets May 17, 11:00 AMAsk anvthina (*4L÷ es CodolSWE.1GW Windsurf Teams 688:10 UTF-84 spaces...
|
iTerm2
|
screenpipe"
|
NULL
|
47815
|
|
49321
|
Last login: Mon May 18 09:17:28 on ttys007
Poetry Last login: Mon May 18 09:17:28 on ttys007
Poetry could not find a pyproject.toml file in /Users/lukas/jiminny/app or its parents
Poetry could not find a pyproject.toml file in /Users/lukas/jiminny/app or its parents
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/jiminny/app (pipedrive-sdk-poc) $ cd ~/.screenpipe
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/.screenpipe $ du -sh ~/.screenpipe
10G /Users/lukas/.screenpipe
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/.screenpipe $ ~/.screenpipe/scripts/screenpipe_sync.sh 2026-05-15
[2026-05-18 09:19:59] ========================================
[2026-05-18 09:19:59] Screenpipe sync starting for: 2026-05-15
[2026-05-18 09:19:59] ========================================
[+00m00s] ▶ Preflight checks
Source DB: OK (7.1G)
[2026-05-18 09:19:59] ERROR: NAS not mounted at /Volumes/screenpipe
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/.screenpipe $ ~/.screenpipe/scripts/screenpipe_sync.sh 2026-05-15
[2026-05-18 09:20:16] ========================================
[2026-05-18 09:20:16] Screenpipe sync starting for: 2026-05-15
[2026-05-18 09:20:16] ========================================
[+00m00s] ▶ Preflight checks
Source DB: OK (7.1G)
NAS mount: OK /Volumes/screenpipe
Archive DB: exists (6.1G)
Data dir: OK (114 files, 146M)
[+00m05s] ▶ Counting source rows for 2026-05-15
frames: 3231
elements: 417620
ui_events: 3376
ocr_text: 1366
meetings: 2
audio_chunks: 593
audio_transcriptions: 15
[+00m06s] ▶ Initialising tables, indexes, FTS
creating tables ✓ 0m00s
creating indexes ✓ 0m00s
creating FTS tables ✓ 0m00s
[+00m06s] ▶ Syncing vision data for 2026-05-15
video_chunks ✓ 0m04s
frames (3231 rows) ✓ 0m52s
ocr_text (1366 rows) ✓ 0m30s
ui_events (3376 rows) ✓ 0m01s
elements (417620 rows) ✓ 0m37s
meetings (2 rows) ✓ 0m00s
[+02m10s] ▶ Syncing audio data for 2026-05-15
audio_chunks (593 rows) ✓ 0m01s
audio_transcriptions (15 rows) ✓ 0m00s
[+02m11s] ▶ Updating FTS indexes
elements_fts ✓ 1m13s
frames_fts ✓ 1m51s
ui_events_fts ✓ 0m02s
audio_transcriptions_fts ✓ 0m01s
[+05m18s] ▶ Verifying DB
frames: 3231 / 3231 ✓
elements: 417620 / 417620 ✓
ui_events: 3376 / 3376 ✓
ocr_text: 1366 / 1366 ✓
meetings: 2 / 2 ✓
audio_chunks: 593 / 593 ✓
audio_transcriptions: 15 / 15 ✓
[+06m17s] ▶ Copying data folder for 2026-05-15
rsync 2026-05-15/ → NAS ✓ 0m10s (114 files, 146M)
[+06m27s] ▶ Copying audio files for 2026-05-15
rsync System Audio (output)_2026-05-15_06-26-46.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-26-46.mp4 → NAS ✓ 8.0K
rsync System Audio (output)_2026-05-15_06-27-10.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-27-18.mp4 → NAS ✓ 70K
rsync System Audio (output)_2026-05-15_06-27-32.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-27-55.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-27-48.mp4 → NAS ✓ 96K
rsync System Audio (output)_2026-05-15_06-28-17.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-28-18.mp4 → NAS ✓ 79K
rsync System Audio (output)_2026-05-15_06-28-39.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-28-48.mp4 → NAS ✓ 80K
rsync System Audio (output)_2026-05-15_06-29-02.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-29-24.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-29-18.mp4 → NAS ✓ 133K
rsync System Audio (output)_2026-05-15_06-29-47.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-29-48.mp4 → NAS ✓ 90K
rsync System Audio (output)_2026-05-15_06-30-09.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-30-18.mp4 → NAS ✓ 80K
rsync System Audio (output)_2026-05-15_06-30-32.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-30-54.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-30-48.mp4 → NAS ✓ 8.0K
rsync System Audio (output)_2026-05-15_06-31-17.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-31-18.mp4 → NAS ✓ 10K
rsync System Audio (output)_2026-05-15_06-31-39.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-31-48.mp4 → NAS ✓ 31K
rsync System Audio (output)_2026-05-15_06-32-01.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-32-24.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-32-18.mp4 → NAS ✓ 74K
rsync System Audio (output)_2026-05-15_06-32-46.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-32-48.mp4 → NAS ✓ 108K
rsync System Audio (output)_2026-05-15_06-33-09.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-33-18.mp4 → NAS ✓ 87K
rsync System Audio (output)_2026-05-15_06-33-31.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-33-54.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-33-48.mp4 → NAS ✓ 13K
rsync System Audio (output)_2026-05-15_06-34-16.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-34-39.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-34-32.mp4 → NAS ✓ 18K
rsync System Audio (output)_2026-05-15_06-35-01.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-35-04.mp4 → NAS ✓ 7.0K
rsync System Audio (output)_2026-05-15_06-35-23.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-35-34.mp4 → NAS ✓ 54K
rsync System Audio (output)_2026-05-15_06-35-46.mp4 → NAS ✓ 5.0K
rsync System Audio (output)_2026-05-15_06-36-08.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_06-36-04.mp4 → NAS ✓ 49K
rsync soundcore AeroClip (input)_2026-05-15_06-36-34.mp4 → NAS ✓ 62K
rsync soundcore AeroClip (input)_2026-05-15_06-40-43.mp4 → NAS ✓ 74K
rsync soundcore AeroClip (input)_2026-05-15_06-41-15.mp4 → NAS ✓ 49K
rsync soundcore AeroClip (input)_2026-05-15_06-41-45.mp4 → NAS ✓ 48K
rsync soundcore AeroClip (input)_2026-05-15_06-42-04.mp4 → NAS ✓ 6.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-42-04.mp4 → NAS ✓ 5.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-42-36.mp4 → NAS ✓ 5.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-43-06.mp4 → NAS ✓ 5.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-43-36.mp4 → NAS ✓ 5.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-44-06.mp4 → NAS ✓ 5.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-44-36.mp4 → NAS ✓ 5.0K
rsync LakyLak bose qc35 II (input)_2026-05-15_06-45-06.mp4 → NAS ✓ 5.0K
rsync MacBook Pro Microphone (input)_2026-05-15_06-45-45.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_06-46-17.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_06-46-47.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_06-47-16.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_06-47-46.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_06-48-16.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_06-48-46.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_06-49-15.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_06-49-45.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_06-50-15.mp4 → NAS ✓ 211K
rsync MacBook Pro Microphone (input)_2026-05-15_06-50-45.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_06-51-15.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_06-51-44.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_06-52-14.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_06-52-44.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_06-53-14.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_06-53-44.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_06-54-14.mp4 → NAS ✓ 100K
rsync MacBook Pro Microphone (input)_2026-05-15_06-54-28.mp4 → NAS ✓ 16K
rsync MacBook Pro Microphone (input)_2026-05-15_06-54-51.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_06-55-24.mp4 → NAS ✓ 207K
rsync MacBook Pro Microphone (input)_2026-05-15_06-55-53.mp4 → NAS ✓ 211K
rsync MacBook Pro Microphone (input)_2026-05-15_06-56-23.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_06-56-53.mp4 → NAS ✓ 217K
rsync MacBook Pro Microphone (input)_2026-05-15_06-57-23.mp4 → NAS ✓ 213K
rsync MacBook Pro Microphone (input)_2026-05-15_06-57-52.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_06-58-22.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_06-58-52.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_06-59-22.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_06-59-52.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_07-00-21.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_07-00-51.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_07-01-20.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_07-01-50.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_07-02-20.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_07-02-50.mp4 → NAS ✓ 207K
rsync MacBook Pro Microphone (input)_2026-05-15_07-03-20.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_07-03-50.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_07-04-20.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_07-04-50.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_07-05-19.mp4 → NAS ✓ 92K
rsync MacBook Pro Microphone (input)_2026-05-15_07-05-33.mp4 → NAS ✓ 14K
rsync soundcore AeroClip (input)_2026-05-15_07-05-33.mp4 → NAS ✓ 28K
rsync soundcore AeroClip (input)_2026-05-15_07-06-05.mp4 → NAS ✓ 65K
rsync soundcore AeroClip (input)_2026-05-15_07-06-35.mp4 → NAS ✓ 44K
rsync soundcore AeroClip (input)_2026-05-15_07-07-05.mp4 → NAS ✓ 66K
rsync soundcore AeroClip (input)_2026-05-15_07-07-35.mp4 → NAS ✓ 114K
rsync soundcore AeroClip (input)_2026-05-15_07-08-05.mp4 → NAS ✓ 61K
rsync soundcore AeroClip (input)_2026-05-15_07-08-35.mp4 → NAS ✓ 96K
rsync soundcore AeroClip (input)_2026-05-15_07-09-05.mp4 → NAS ✓ 44K
rsync soundcore AeroClip (input)_2026-05-15_07-09-35.mp4 → NAS ✓ 38K
rsync soundcore AeroClip (input)_2026-05-15_07-10-05.mp4 → NAS ✓ 11K
rsync soundcore AeroClip (input)_2026-05-15_07-10-35.mp4 → NAS ✓ 31K
rsync soundcore AeroClip (input)_2026-05-15_07-11-05.mp4 → NAS ✓ 55K
rsync soundcore AeroClip (input)_2026-05-15_07-11-35.mp4 → NAS ✓ 51K
rsync soundcore AeroClip (input)_2026-05-15_07-12-04.mp4 → NAS ✓ 36K
rsync soundcore AeroClip (input)_2026-05-15_07-12-34.mp4 → NAS ✓ 24K
rsync soundcore AeroClip (input)_2026-05-15_07-13-04.mp4 → NAS ✓ 25K
rsync soundcore AeroClip (input)_2026-05-15_07-13-34.mp4 → NAS ✓ 9.0K
rsync soundcore AeroClip (input)_2026-05-15_07-14-04.mp4 → NAS ✓ 39K
rsync soundcore AeroClip (input)_2026-05-15_07-14-34.mp4 → NAS ✓ 31K
rsync soundcore AeroClip (input)_2026-05-15_07-15-04.mp4 → NAS ✓ 28K
rsync soundcore AeroClip (input)_2026-05-15_07-15-34.mp4 → NAS ✓ 35K
rsync soundcore AeroClip (input)_2026-05-15_07-16-04.mp4 → NAS ✓ 44K
rsync soundcore AeroClip (input)_2026-05-15_07-16-34.mp4 → NAS ✓ 31K
rsync soundcore AeroClip (input)_2026-05-15_07-17-04.mp4 → NAS ✓ 27K
rsync soundcore AeroClip (input)_2026-05-15_07-17-34.mp4 → NAS ✓ 22K
rsync soundcore AeroClip (input)_2026-05-15_07-18-04.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_07-18-34.mp4 → NAS ✓ 25K
rsync soundcore AeroClip (input)_2026-05-15_07-19-04.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_07-19-34.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_07-20-04.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_07-20-34.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_07-21-04.mp4 → NAS ✓ 15K
rsync soundcore AeroClip (input)_2026-05-15_07-21-34.mp4 → NAS ✓ 14K
rsync soundcore AeroClip (input)_2026-05-15_07-22-04.mp4 → NAS ✓ 8.0K
rsync soundcore AeroClip (input)_2026-05-15_07-22-34.mp4 → NAS ✓ 8.0K
rsync soundcore AeroClip (input)_2026-05-15_07-23-04.mp4 → NAS ✓ 9.0K
rsync soundcore AeroClip (input)_2026-05-15_07-23-34.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_07-24-04.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_07-24-34.mp4 → NAS ✓ 15K
rsync soundcore AeroClip (input)_2026-05-15_07-25-04.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_07-25-38.mp4 → NAS ✓ 9.0K
rsync soundcore AeroClip (input)_2026-05-15_07-26-10.mp4 → NAS ✓ 12K
rsync soundcore AeroClip (input)_2026-05-15_07-26-40.mp4 → NAS ✓ 11K
rsync soundcore AeroClip (input)_2026-05-15_07-27-10.mp4 → NAS ✓ 12K
rsync soundcore AeroClip (input)_2026-05-15_07-27-40.mp4 → NAS ✓ 8.0K
rsync soundcore AeroClip (input)_2026-05-15_07-28-20.mp4 → NAS ✓ 25K
rsync soundcore AeroClip (input)_2026-05-15_07-28-52.mp4 → NAS ✓ 12K
rsync soundcore AeroClip (input)_2026-05-15_07-29-21.mp4 → NAS ✓ 12K
rsync soundcore AeroClip (input)_2026-05-15_07-29-51.mp4 → NAS ✓ 8.0K
rsync soundcore AeroClip (input)_2026-05-15_07-30-25.mp4 → NAS ✓ 13K
rsync soundcore AeroClip (input)_2026-05-15_07-30-57.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_07-31-27.mp4 → NAS ✓ 11K
rsync soundcore AeroClip (input)_2026-05-15_07-31-57.mp4 → NAS ✓ 9.0K
rsync soundcore AeroClip (input)_2026-05-15_07-32-27.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_07-32-57.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_07-33-38.mp4 → NAS ✓ 22K
rsync soundcore AeroClip (input)_2026-05-15_07-34-10.mp4 → NAS ✓ 72K
rsync soundcore AeroClip (input)_2026-05-15_07-34-40.mp4 → NAS ✓ 74K
rsync soundcore AeroClip (input)_2026-05-15_07-35-10.mp4 → NAS ✓ 63K
rsync soundcore AeroClip (input)_2026-05-15_07-35-40.mp4 → NAS ✓ 14K
rsync soundcore AeroClip (input)_2026-05-15_07-36-10.mp4 → NAS ✓ 21K
rsync soundcore AeroClip (input)_2026-05-15_07-36-39.mp4 → NAS ✓ 35K
rsync soundcore AeroClip (input)_2026-05-15_07-37-09.mp4 → NAS ✓ 46K
rsync soundcore AeroClip (input)_2026-05-15_07-37-39.mp4 → NAS ✓ 40K
rsync soundcore AeroClip (input)_2026-05-15_07-38-09.mp4 → NAS ✓ 26K
rsync soundcore AeroClip (input)_2026-05-15_07-38-39.mp4 → NAS ✓ 29K
rsync soundcore AeroClip (input)_2026-05-15_07-39-09.mp4 → NAS ✓ 49K
rsync soundcore AeroClip (input)_2026-05-15_07-39-39.mp4 → NAS ✓ 37K
rsync soundcore AeroClip (input)_2026-05-15_07-40-09.mp4 → NAS ✓ 56K
rsync soundcore AeroClip (input)_2026-05-15_07-40-39.mp4 → NAS ✓ 39K
rsync soundcore AeroClip (input)_2026-05-15_07-41-09.mp4 → NAS ✓ 37K
rsync soundcore AeroClip (input)_2026-05-15_07-41-38.mp4 → NAS ✓ 159K
rsync soundcore AeroClip (input)_2026-05-15_07-42-08.mp4 → NAS ✓ 69K
rsync soundcore AeroClip (input)_2026-05-15_07-42-38.mp4 → NAS ✓ 51K
rsync soundcore AeroClip (input)_2026-05-15_07-43-08.mp4 → NAS ✓ 30K
rsync soundcore AeroClip (input)_2026-05-15_07-43-38.mp4 → NAS ✓ 33K
rsync soundcore AeroClip (input)_2026-05-15_07-44-08.mp4 → NAS ✓ 71K
rsync soundcore AeroClip (input)_2026-05-15_07-44-38.mp4 → NAS ✓ 38K
rsync soundcore AeroClip (input)_2026-05-15_07-45-08.mp4 → NAS ✓ 21K
rsync soundcore AeroClip (input)_2026-05-15_07-45-38.mp4 → NAS ✓ 37K
rsync soundcore AeroClip (input)_2026-05-15_07-46-08.mp4 → NAS ✓ 50K
rsync soundcore AeroClip (input)_2026-05-15_07-46-38.mp4 → NAS ✓ 26K
rsync soundcore AeroClip (input)_2026-05-15_07-47-08.mp4 → NAS ✓ 32K
rsync soundcore AeroClip (input)_2026-05-15_07-47-38.mp4 → NAS ✓ 14K
rsync soundcore AeroClip (input)_2026-05-15_07-48-08.mp4 → NAS ✓ 32K
rsync soundcore AeroClip (input)_2026-05-15_07-48-38.mp4 → NAS ✓ 62K
rsync soundcore AeroClip (input)_2026-05-15_07-49-08.mp4 → NAS ✓ 110K
rsync soundcore AeroClip (input)_2026-05-15_07-49-38.mp4 → NAS ✓ 51K
rsync soundcore AeroClip (input)_2026-05-15_07-50-08.mp4 → NAS ✓ 35K
rsync soundcore AeroClip (input)_2026-05-15_07-50-38.mp4 → NAS ✓ 81K
rsync soundcore AeroClip (input)_2026-05-15_07-51-08.mp4 → NAS ✓ 72K
rsync soundcore AeroClip (input)_2026-05-15_07-51-38.mp4 → NAS ✓ 26K
rsync soundcore AeroClip (input)_2026-05-15_07-52-08.mp4 → NAS ✓ 22K
rsync soundcore AeroClip (input)_2026-05-15_07-52-38.mp4 → NAS ✓ 17K
rsync soundcore AeroClip (input)_2026-05-15_07-53-08.mp4 → NAS ✓ 14K
rsync soundcore AeroClip (input)_2026-05-15_07-53-37.mp4 → NAS ✓ 21K
rsync soundcore AeroClip (input)_2026-05-15_07-54-07.mp4 → NAS ✓ 28K
rsync soundcore AeroClip (input)_2026-05-15_07-54-37.mp4 → NAS ✓ 19K
rsync soundcore AeroClip (input)_2026-05-15_07-55-07.mp4 → NAS ✓ 17K
rsync soundcore AeroClip (input)_2026-05-15_07-55-37.mp4 → NAS ✓ 15K
rsync soundcore AeroClip (input)_2026-05-15_07-56-07.mp4 → NAS ✓ 16K
rsync soundcore AeroClip (input)_2026-05-15_07-56-37.mp4 → NAS ✓ 16K
rsync soundcore AeroClip (input)_2026-05-15_07-57-07.mp4 → NAS ✓ 11K
rsync soundcore AeroClip (input)_2026-05-15_07-57-37.mp4 → NAS ✓ 8.0K
rsync soundcore AeroClip (input)_2026-05-15_07-58-07.mp4 → NAS ✓ 15K
rsync soundcore AeroClip (input)_2026-05-15_07-58-37.mp4 → NAS ✓ 15K
rsync soundcore AeroClip (input)_2026-05-15_07-59-07.mp4 → NAS ✓ 17K
rsync soundcore AeroClip (input)_2026-05-15_07-59-37.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_08-00-26.mp4 → NAS ✓ 9.0K
rsync soundcore AeroClip (input)_2026-05-15_08-00-58.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_08-01-47.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_08-02-43.mp4 → NAS ✓ 18K
rsync soundcore AeroClip (input)_2026-05-15_08-03-20.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_08-03-52.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_08-04-22.mp4 → NAS ✓ 9.0K
rsync soundcore AeroClip (input)_2026-05-15_08-04-52.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_08-05-37.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_08-06-09.mp4 → NAS ✓ 7.0K
rsync soundcore AeroClip (input)_2026-05-15_08-08-20.mp4 → NAS ✓ 13K
rsync soundcore AeroClip (input)_2026-05-15_08-08-52.mp4 → NAS ✓ 6.0K
rsync soundcore AeroClip (input)_2026-05-15_08-09-36.mp4 → NAS ✓ 12K
rsync soundcore AeroClip (input)_2026-05-15_08-10-08.mp4 → NAS ✓ 10K
rsync soundcore AeroClip (input)_2026-05-15_08-10-38.mp4 → NAS ✓ 45K
rsync soundcore AeroClip (input)_2026-05-15_08-11-08.mp4 → NAS ✓ 62K
rsync soundcore AeroClip (input)_2026-05-15_08-11-38.mp4 → NAS ✓ 23K
rsync soundcore AeroClip (input)_2026-05-15_08-12-08.mp4 → NAS ✓ 26K
rsync soundcore AeroClip (input)_2026-05-15_08-12-38.mp4 → NAS ✓ 13K
rsync soundcore AeroClip (input)_2026-05-15_08-13-08.mp4 → NAS ✓ 16K
rsync soundcore AeroClip (input)_2026-05-15_08-13-38.mp4 → NAS ✓ 14K
rsync soundcore AeroClip (input)_2026-05-15_08-14-08.mp4 → NAS ✓ 16K
rsync soundcore AeroClip (input)_2026-05-15_08-14-38.mp4 → NAS ✓ 20K
rsync soundcore AeroClip (input)_2026-05-15_08-15-31.mp4 → NAS ✓ 5.0K
rsync soundcore AeroClip (input)_2026-05-15_08-16-03.mp4 → NAS ✓ 21K
rsync MacBook Pro Microphone (input)_2026-05-15_08-17-04.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-17-35.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_08-18-05.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_08-18-35.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_08-19-05.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_08-19-35.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_08-20-05.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_08-20-35.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_08-21-05.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_08-21-34.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_08-22-04.mp4 → NAS ✓ 213K
rsync MacBook Pro Microphone (input)_2026-05-15_08-22-34.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_08-23-04.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-23-34.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_08-24-04.mp4 → NAS ✓ 234K
rsync MacBook Pro Microphone (input)_2026-05-15_08-24-33.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_08-25-03.mp4 → NAS ✓ 211K
rsync MacBook Pro Microphone (input)_2026-05-15_08-25-33.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_08-26-03.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-26-33.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_08-27-03.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_08-27-32.mp4 → NAS ✓ 215K
rsync MacBook Pro Microphone (input)_2026-05-15_08-28-02.mp4 → NAS ✓ 225K
rsync MacBook Pro Microphone (input)_2026-05-15_08-28-32.mp4 → NAS ✓ 224K
rsync MacBook Pro Microphone (input)_2026-05-15_08-29-02.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_08-29-32.mp4 → NAS ✓ 188K
rsync MacBook Pro Microphone (input)_2026-05-15_08-30-02.mp4 → NAS ✓ 185K
rsync MacBook Pro Microphone (input)_2026-05-15_08-30-32.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_08-31-02.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-31-32.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_08-32-01.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_08-32-31.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-33-01.mp4 → NAS ✓ 235K
rsync MacBook Pro Microphone (input)_2026-05-15_08-33-31.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_08-34-01.mp4 → NAS ✓ 224K
rsync MacBook Pro Microphone (input)_2026-05-15_08-34-30.mp4 → NAS ✓ 218K
rsync MacBook Pro Microphone (input)_2026-05-15_08-35-00.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_08-35-30.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_08-35-59.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_08-36-29.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_08-36-59.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-37-29.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-37-59.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_08-38-28.mp4 → NAS ✓ 214K
rsync MacBook Pro Microphone (input)_2026-05-15_08-38-58.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_08-39-28.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_08-39-58.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_08-40-27.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_08-40-57.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_08-41-27.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_08-41-56.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_08-42-26.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_08-42-56.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-43-26.mp4 → NAS ✓ 211K
rsync MacBook Pro Microphone (input)_2026-05-15_08-43-56.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_08-44-25.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_08-44-55.mp4 → NAS ✓ 207K
rsync MacBook Pro Microphone (input)_2026-05-15_08-45-24.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_08-45-54.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_08-46-24.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_08-46-54.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_08-47-24.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_08-47-54.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_08-48-24.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_08-48-54.mp4 → NAS ✓ 220K
rsync MacBook Pro Microphone (input)_2026-05-15_08-49-24.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_08-49-54.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_08-50-23.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_08-50-53.mp4 → NAS ✓ 232K
rsync MacBook Pro Microphone (input)_2026-05-15_08-51-22.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_08-51-52.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_08-52-22.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_08-52-51.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_08-53-21.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-53-51.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_08-54-21.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_08-54-50.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_08-55-20.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_08-55-50.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-56-20.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_08-56-49.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_08-57-19.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_08-57-49.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_08-58-18.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_08-58-48.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_08-59-18.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_08-59-48.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_09-00-18.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_09-00-47.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_09-01-17.mp4 → NAS ✓ 214K
rsync MacBook Pro Microphone (input)_2026-05-15_09-01-47.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_09-02-16.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_09-02-46.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_09-03-16.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_09-03-46.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_09-04-16.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_09-04-46.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_09-05-15.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_09-05-45.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_09-06-15.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_09-06-45.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_09-07-15.mp4 → NAS ✓ 215K
rsync MacBook Pro Microphone (input)_2026-05-15_09-07-45.mp4 → NAS ✓ 236K
rsync MacBook Pro Microphone (input)_2026-05-15_09-08-15.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_09-08-44.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_09-09-14.mp4 → NAS ✓ 217K
rsync MacBook Pro Microphone (input)_2026-05-15_09-09-44.mp4 → NAS ✓ 219K
rsync MacBook Pro Microphone (input)_2026-05-15_09-10-14.mp4 → NAS ✓ 219K
rsync MacBook Pro Microphone (input)_2026-05-15_09-10-43.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_09-11-13.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_09-11-43.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_09-12-13.mp4 → NAS ✓ 187K
rsync MacBook Pro Microphone (input)_2026-05-15_09-12-43.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_09-13-13.mp4 → NAS ✓ 207K
rsync MacBook Pro Microphone (input)_2026-05-15_09-13-42.mp4 → NAS ✓ 223K
rsync MacBook Pro Microphone (input)_2026-05-15_09-14-12.mp4 → NAS ✓ 223K
rsync MacBook Pro Microphone (input)_2026-05-15_09-14-42.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_09-15-12.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_09-15-41.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_09-16-11.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_09-16-41.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_09-17-11.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_09-17-41.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_09-18-11.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_09-18-41.mp4 → NAS ✓ 187K
rsync MacBook Pro Microphone (input)_2026-05-15_09-19-11.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_09-19-41.mp4 → NAS ✓ 187K
rsync MacBook Pro Microphone (input)_2026-05-15_09-20-11.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_09-20-41.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_09-21-10.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_09-21-40.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_09-22-10.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_09-22-40.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_09-23-10.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_09-23-40.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_09-24-10.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_09-24-39.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_09-25-09.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_09-25-39.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_09-26-09.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_09-26-39.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_09-27-08.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_09-27-38.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_09-28-08.mp4 → NAS ✓ 225K
rsync MacBook Pro Microphone (input)_2026-05-15_09-28-38.mp4 → NAS ✓ 240K
rsync MacBook Pro Microphone (input)_2026-05-15_09-29-08.mp4 → NAS ✓ 215K
rsync MacBook Pro Microphone (input)_2026-05-15_09-29-38.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_09-30-07.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_09-30-37.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_09-31-07.mp4 → NAS ✓ 235K
rsync MacBook Pro Microphone (input)_2026-05-15_09-31-37.mp4 → NAS ✓ 220K
rsync MacBook Pro Microphone (input)_2026-05-15_09-32-06.mp4 → NAS ✓ 214K
rsync MacBook Pro Microphone (input)_2026-05-15_09-32-36.mp4 → NAS ✓ 220K
rsync MacBook Pro Microphone (input)_2026-05-15_09-33-06.mp4 → NAS ✓ 228K
rsync MacBook Pro Microphone (input)_2026-05-15_09-33-36.mp4 → NAS ✓ 232K
rsync MacBook Pro Microphone (input)_2026-05-15_09-34-05.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_09-34-35.mp4 → NAS ✓ 235K
rsync MacBook Pro Microphone (input)_2026-05-15_09-35-05.mp4 → NAS ✓ 219K
rsync MacBook Pro Microphone (input)_2026-05-15_09-35-35.mp4 → NAS ✓ 227K
rsync MacBook Pro Microphone (input)_2026-05-15_09-36-04.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_09-36-34.mp4 → NAS ✓ 231K
rsync MacBook Pro Microphone (input)_2026-05-15_09-37-04.mp4 → NAS ✓ 230K
rsync MacBook Pro Microphone (input)_2026-05-15_09-37-34.mp4 → NAS ✓ 241K
rsync MacBook Pro Microphone (input)_2026-05-15_09-38-03.mp4 → NAS ✓ 215K
rsync MacBook Pro Microphone (input)_2026-05-15_09-38-33.mp4 → NAS ✓ 226K
rsync MacBook Pro Microphone (input)_2026-05-15_09-39-03.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_09-39-33.mp4 → NAS ✓ 227K
rsync MacBook Pro Microphone (input)_2026-05-15_09-40-02.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_09-40-32.mp4 → NAS ✓ 207K
rsync MacBook Pro Microphone (input)_2026-05-15_09-41-02.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_09-41-32.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_09-42-02.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_09-42-32.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_09-43-02.mp4 → NAS ✓ 187K
rsync MacBook Pro Microphone (input)_2026-05-15_09-43-32.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_09-44-01.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_09-44-31.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_09-45-01.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_09-45-31.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_09-46-01.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_09-46-31.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_09-47-01.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_09-47-31.mp4 → NAS ✓ 187K
rsync MacBook Pro Microphone (input)_2026-05-15_09-48-01.mp4 → NAS ✓ 188K
rsync MacBook Pro Microphone (input)_2026-05-15_09-48-31.mp4 → NAS ✓ 185K
rsync MacBook Pro Microphone (input)_2026-05-15_09-49-01.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_09-49-31.mp4 → NAS ✓ 186K
rsync MacBook Pro Microphone (input)_2026-05-15_09-50-01.mp4 → NAS ✓ 186K
rsync MacBook Pro Microphone (input)_2026-05-15_09-50-31.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_09-51-00.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_09-51-30.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_09-52-00.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_09-58-06.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_09-58-37.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_09-59-07.mp4 → NAS ✓ 190K
rsync MacBook Pro Microphone (input)_2026-05-15_09-59-37.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-00-07.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-00-37.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_10-01-07.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_10-01-37.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_10-02-07.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_10-02-37.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-03-07.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-03-36.mp4 → NAS ✓ 231K
rsync MacBook Pro Microphone (input)_2026-05-15_10-04-06.mp4 → NAS ✓ 191K
rsync MacBook Pro Microphone (input)_2026-05-15_10-04-36.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-05-06.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-05-36.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_10-06-06.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_10-06-36.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_10-07-06.mp4 → NAS ✓ 215K
rsync MacBook Pro Microphone (input)_2026-05-15_10-07-36.mp4 → NAS ✓ 218K
rsync MacBook Pro Microphone (input)_2026-05-15_10-08-05.mp4 → NAS ✓ 199K
rsync MacBook Pro Microphone (input)_2026-05-15_10-08-35.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-09-05.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_10-09-35.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_10-10-05.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-10-34.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_10-11-04.mp4 → NAS ✓ 188K
rsync MacBook Pro Microphone (input)_2026-05-15_10-11-34.mp4 → NAS ✓ 185K
rsync MacBook Pro Microphone (input)_2026-05-15_10-12-04.mp4 → NAS ✓ 187K
rsync MacBook Pro Microphone (input)_2026-05-15_10-12-34.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_10-13-04.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_10-13-34.mp4 → NAS ✓ 230K
rsync MacBook Pro Microphone (input)_2026-05-15_10-14-03.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_10-14-33.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_10-15-03.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_10-15-33.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_10-16-03.mp4 → NAS ✓ 215K
rsync MacBook Pro Microphone (input)_2026-05-15_10-16-33.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_10-17-03.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-17-33.mp4 → NAS ✓ 208K
rsync MacBook Pro Microphone (input)_2026-05-15_10-18-03.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_10-18-32.mp4 → NAS ✓ 188K
rsync MacBook Pro Microphone (input)_2026-05-15_10-19-02.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_10-19-32.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-20-02.mp4 → NAS ✓ 206K
rsync MacBook Pro Microphone (input)_2026-05-15_10-20-32.mp4 → NAS ✓ 232K
rsync MacBook Pro Microphone (input)_2026-05-15_10-21-02.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_10-21-31.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_10-22-01.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-22-31.mp4 → NAS ✓ 223K
rsync MacBook Pro Microphone (input)_2026-05-15_10-23-01.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-23-31.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-24-01.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_10-24-30.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_10-25-00.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_10-25-30.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_10-26-00.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_10-26-30.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_10-27-00.mp4 → NAS ✓ 229K
rsync MacBook Pro Microphone (input)_2026-05-15_10-27-30.mp4 → NAS ✓ 235K
rsync MacBook Pro Microphone (input)_2026-05-15_10-28-00.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_10-28-30.mp4 → NAS ✓ 224K
rsync MacBook Pro Microphone (input)_2026-05-15_10-29-00.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_10-29-30.mp4 → NAS ✓ 236K
rsync MacBook Pro Microphone (input)_2026-05-15_10-29-59.mp4 → NAS ✓ 232K
rsync MacBook Pro Microphone (input)_2026-05-15_10-30-29.mp4 → NAS ✓ 211K
rsync MacBook Pro Microphone (input)_2026-05-15_10-30-59.mp4 → NAS ✓ 211K
rsync MacBook Pro Microphone (input)_2026-05-15_10-31-29.mp4 → NAS ✓ 226K
rsync MacBook Pro Microphone (input)_2026-05-15_10-31-59.mp4 → NAS ✓ 240K
rsync MacBook Pro Microphone (input)_2026-05-15_10-32-28.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_10-32-58.mp4 → NAS ✓ 216K
rsync MacBook Pro Microphone (input)_2026-05-15_10-33-28.mp4 → NAS ✓ 243K
rsync MacBook Pro Microphone (input)_2026-05-15_10-33-58.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_10-34-27.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_10-34-57.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-35-27.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_10-35-57.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_10-36-27.mp4 → NAS ✓ 200K
rsync MacBook Pro Microphone (input)_2026-05-15_10-36-57.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_10-37-27.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_10-37-57.mp4 → NAS ✓ 210K
rsync MacBook Pro Microphone (input)_2026-05-15_10-38-27.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_10-38-57.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_10-39-26.mp4 → NAS ✓ 228K
rsync MacBook Pro Microphone (input)_2026-05-15_10-39-56.mp4 → NAS ✓ 217K
rsync MacBook Pro Microphone (input)_2026-05-15_10-40-26.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-40-56.mp4 → NAS ✓ 189K
rsync MacBook Pro Microphone (input)_2026-05-15_10-41-26.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-41-56.mp4 → NAS ✓ 229K
rsync MacBook Pro Microphone (input)_2026-05-15_10-42-26.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-42-55.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_10-43-25.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-43-55.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_10-44-25.mp4 → NAS ✓ 212K
rsync MacBook Pro Microphone (input)_2026-05-15_10-44-55.mp4 → NAS ✓ 225K
rsync MacBook Pro Microphone (input)_2026-05-15_10-45-25.mp4 → NAS ✓ 203K
rsync MacBook Pro Microphone (input)_2026-05-15_10-45-55.mp4 → NAS ✓ 207K
rsync MacBook Pro Microphone (input)_2026-05-15_10-46-24.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_10-46-54.mp4 → NAS ✓ 193K
rsync MacBook Pro Microphone (input)_2026-05-15_10-47-24.mp4 → NAS ✓ 198K
rsync MacBook Pro Microphone (input)_2026-05-15_10-47-54.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-48-23.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-48-53.mp4 → NAS ✓ 205K
rsync MacBook Pro Microphone (input)_2026-05-15_10-49-23.mp4 → NAS ✓ 202K
rsync MacBook Pro Microphone (input)_2026-05-15_10-49-53.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-50-23.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-50-52.mp4 → NAS ✓ 194K
rsync MacBook Pro Microphone (input)_2026-05-15_10-51-22.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_10-51-52.mp4 → NAS ✓ 204K
rsync MacBook Pro Microphone (input)_2026-05-15_10-52-22.mp4 → NAS ✓ 192K
rsync MacBook Pro Microphone (input)_2026-05-15_10-52-51.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_10-53-21.mp4 → NAS ✓ 201K
rsync MacBook Pro Microphone (input)_2026-05-15_10-53-51.mp4 → NAS ✓ 195K
rsync MacBook Pro Microphone (input)_2026-05-15_10-54-21.mp4 → NAS ✓ 196K
rsync MacBook Pro Microphone (input)_2026-05-15_10-54-51.mp4 → NAS ✓ 197K
rsync MacBook Pro Microphone (input)_2026-05-15_10-55-21.mp4 → NAS ✓ 209K
rsync MacBook Pro Microphone (input)_2026-05-15_10-55-50.mp4 → NAS ✓ 235K
...
|
iTerm2
|
screenpipe"
|
NULL
|
49321
|