|
14919
|
whisper_backend_init_gpu: found GPU device 0: Meta whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-10T23:27:31.985285Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-10T23:27:41.489329Z ERROR screenpipe_audio::core::stream: an error occurred on the audio stream: device disconnected
2026-05-10T23:27:42.161846Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)
2026-05-10T23:27:42.163527Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-10T23:27:42.164408Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)
2026-05-10T23:27:42.164471Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-10T23:27:42.164492Z INFO screenpipe_audio::core::run_record_and_transcribe: screen locked, pausing audio recording for MacBook Pro Microphone (input)
2026-05-10T23:27:42.881174Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for soundcore AeroClip (input)
2026-05-10T23:27:43.285854Z INFO screenpipe_audio::transcription::handle_new_transcript: device soundcore AeroClip (input) skipping duplicate transcript (entire content overlaps with previous)
2026-05-10T23:27:58.189174Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: soundcore AeroClip (input)
2026-05-10T23:27:58.190264Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-10T23:27:58.190299Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: soundcore AeroClip (input)
2026-05-10T23:27:58.190324Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-10T23:27:58.190332Z INFO screenpipe_audio::core::run_record_and_transcribe: screen locked, pausing audio recording for soundcore AeroClip (input)
2026-05-10T23:27:58.203316Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for MacBook Pro Microphone (input)
2026-05-10T23:28:32.063312Z ERROR screenpipe_audio::core::stream: an error occurred on the audio stream: device disconnected
2026-05-10T23:28:32.531328Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: MacBook Pro Microphone (input)
2026-05-10T23:28:32.531913Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-10T23:28:32.531933Z INFO screenpipe_audio::audio_manager::device_monitor: switched to new system default input: MacBook Pro Microphone (input)
2026-05-10T23:28:32.532003Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for soundcore AeroClip (input)
2026-05-10T23:28:32.708770Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-10T23:28:32.708807Z INFO screenpipe_audio::core::run_record_and_transcribe: screen locked, pausing audio recording for MacBook Pro Microphone (input)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-10T23:51:42.401532Z 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: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T02:54:23.501609Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
2026-05-11T07:21:22.702849Z INFO screenpipe_audio::audio_manager::device_monitor: system default input changed to: soundcore AeroClip (input)
2026-05-11T07:21:22.703351Z ERROR screenpipe_audio::audio_manager::device_monitor: failed to start new default input soundcore AeroClip (input): device soundcore AeroClip (input) not found (will back off)
2026-05-11T07:21:22.704671Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] no input device running (attempt 1), starting default: soundcore AeroClip (input)
2026-05-11T07:21:22.704693Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] failed to start input device soundcore AeroClip (input) (attempt 1): device soundcore AeroClip (input) not found
2026-05-11T07:21:23.587900Z INFO screenpipe_audio::core::run_record_and_transcribe: stopped recording for MacBook Pro Microphone (input)
2026-05-11T07:21:24.708381Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] no input device running (attempt 2), starting default: soundcore AeroClip (input)
2026-05-11T07:21:24.708451Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] failed to start input device soundcore AeroClip (input) (attempt 2): device soundcore AeroClip (input) not found
2026-05-11T07:21:26.711922Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] no input device running (attempt 3), starting default: soundcore AeroClip (input)
2026-05-11T07:21:26.712001Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] failed to start input device soundcore AeroClip (input) (attempt 3): device soundcore AeroClip (input) not found
2026-05-11T07:21:28.723900Z WARN screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] no input device running (attempt 4), starting default: soundcore AeroClip (input)
2026-05-11T07:21:28.726974Z INFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)
2026-05-11T07:21:28.727134Z INFO screenpipe_audio::audio_manager::device_monitor: [DEVICE_RECOVERY] input device restored, device=soundcore AeroClip (input)
2026-05-11T07:21:28.972503Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)
2026-05-11T07:21:28.972538Z INFO screenpipe_audio::core::run_record_and_transcribe: screen locked, pausing audio recording for soundcore AeroClip (input)
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
2026-05-11T07:54:37.325769Z INFO screenpipe_en...
|
iTerm2
|
screenpipe"
|
NULL
|
14919
|