2026-11-01T17:27:36.582699Z [info     ] Started server process [2810880] service_name=monsum-speech
2026-11-01T17:27:36.582830Z [info     ] Waiting for application startup. service_name=monsum-speech
2026-11-01T17:27:36.582968Z [info     ] Application startup complete.  service_name=monsum-speech
2026-11-01T17:27:36.583896Z [info     ] Uvicorn running on http://127.0.0.1:8012 (Press CTRL+C to quit) service_name=monsum-speech
2026-11-01T17:27:41.257475Z [info     ] request.completed              duration_ms=2.65 endpoint=/health method=GET request_id=24eb938d-9ce1-43ea-8690-a8840667bd94 service_name=monsum-speech status_code=200 trace_id=24eb938d-9ce1-43ea-8690-a8840667bd94
2026-11-01T17:27:41.257806Z [info     ] 127.0.0.1:53388 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:27:41.271941Z [info     ] request.completed              duration_ms=0.34 endpoint=/health method=GET request_id=b923b304-d855-4cb8-9281-6c86cd4a0a3b service_name=monsum-speech status_code=200 trace_id=b923b304-d855-4cb8-9281-6c86cd4a0a3b
2026-11-01T17:27:41.272484Z [info     ] 127.0.0.1:53394 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:27:42.927855Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
2026-11-01T17:27:43.951995Z [info     ] asr_language_detected          detected_language=kk diverted=False endpoint=/v1/audio/transcriptions probability=0.1790771484375 request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
2026-11-01T17:27:43.952113Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo-mn-1 request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
2026-11-01T17:27:44.378083Z [info     ] Processing audio with duration 46:25.250 endpoint=/v1/audio/transcriptions request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
2026-11-01T17:27:47.547678Z [info     ] VAD filter removed 02:54.392 of audio endpoint=/v1/audio/transcriptions request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
2026-11-01T17:29:08.762792Z [info     ] transcription_completed        audio_seconds=2785.25 elapsed_ms=84811 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=4 num_segments=211 num_words=8059 request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/pyannote/audio/core/io.py:48: UserWarning: 
torchcodec is not installed correctly so built-in audio decoding will fail. Solutions are:
* use audio preloaded in-memory as a {'waveform': (channel, time) torch.Tensor, 'sample_rate': int} dictionary;
* fix torchcodec installation. Error message was:

Could not load libtorchcodec. Likely causes:
          1. FFmpeg is not properly installed in your environment. We support
             versions 4, 5, 6, 7, and 8, and we attempt to load libtorchcodec
             for each of those versions. Errors for versions not installed on
             your system are expected; only the error for your installed FFmpeg
             version is relevant. On Windows, ensure you've installed the
             "full-shared" version which ships DLLs.
          2. The PyTorch version (2.8.0+cu126) is not compatible with
             this version of TorchCodec. Refer to the version compatibility
             table:
             https://github.com/pytorch/torchcodec?tab=readme-ov-file#installing-torchcodec.
          3. Another runtime dependency; see exceptions below.

        The following exceptions were raised as we tried to load libtorchcodec:
        
[start of libtorchcodec loading traceback]
FFmpeg version 8:
Traceback (most recent call last):
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torchcodec/_internally_replaced_utils.py", line 93, in load_torchcodec_shared_libraries
    torch.ops.load_library(core_library_path)
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torch/_ops.py", line 1478, in load_library
    ctypes.CDLL(path)
  File "/home/bilguun/.local/share/uv/python/cpython-3.12.8-linux-x86_64-gnu/lib/python3.12/ctypes/__init__.py", line 379, in __init__
    self._handle = _dlopen(self._name, mode)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: libavutil.so.60: cannot open shared object file: No such file or directory

FFmpeg version 7:
Traceback (most recent call last):
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torchcodec/_internally_replaced_utils.py", line 93, in load_torchcodec_shared_libraries
    torch.ops.load_library(core_library_path)
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torch/_ops.py", line 1478, in load_library
    ctypes.CDLL(path)
  File "/home/bilguun/.local/share/uv/python/cpython-3.12.8-linux-x86_64-gnu/lib/python3.12/ctypes/__init__.py", line 379, in __init__
    self._handle = _dlopen(self._name, mode)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: libavutil.so.59: cannot open shared object file: No such file or directory

FFmpeg version 6:
Traceback (most recent call last):
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torchcodec/_internally_replaced_utils.py", line 93, in load_torchcodec_shared_libraries
    torch.ops.load_library(core_library_path)
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torch/_ops.py", line 1478, in load_library
    ctypes.CDLL(path)
  File "/home/bilguun/.local/share/uv/python/cpython-3.12.8-linux-x86_64-gnu/lib/python3.12/ctypes/__init__.py", line 379, in __init__
    self._handle = _dlopen(self._name, mode)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: libavutil.so.58: cannot open shared object file: No such file or directory

FFmpeg version 5:
Traceback (most recent call last):
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torchcodec/_internally_replaced_utils.py", line 93, in load_torchcodec_shared_libraries
    torch.ops.load_library(core_library_path)
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torch/_ops.py", line 1478, in load_library
    ctypes.CDLL(path)
  File "/home/bilguun/.local/share/uv/python/cpython-3.12.8-linux-x86_64-gnu/lib/python3.12/ctypes/__init__.py", line 379, in __init__
    self._handle = _dlopen(self._name, mode)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: libavutil.so.57: cannot open shared object file: No such file or directory

FFmpeg version 4:
Traceback (most recent call last):
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torchcodec/_internally_replaced_utils.py", line 93, in load_torchcodec_shared_libraries
    torch.ops.load_library(core_library_path)
  File "/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torch/_ops.py", line 1478, in load_library
    ctypes.CDLL(path)
  File "/home/bilguun/.local/share/uv/python/cpython-3.12.8-linux-x86_64-gnu/lib/python3.12/ctypes/__init__.py", line 379, in __init__
    self._handle = _dlopen(self._name, mode)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: /home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/torchcodec/libtorchcodec_core4.so: undefined symbol: torch_from_blob
[end of libtorchcodec loading traceback].
  warnings.warn(
2026-11-01T17:29:10.196179Z [info     ] diarization_pipeline_loading   device=cuda endpoint=/v1/audio/transcriptions path=models/speaker-diarization-community-1 request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/pyannote/audio/utils/reproducibility.py:74: ReproducibilityWarning: TensorFloat-32 (TF32) has been disabled as it might lead to reproducibility issues and lower accuracy.
It can be re-enabled by calling
   >>> import torch
   >>> torch.backends.cuda.matmul.allow_tf32 = True
   >>> torch.backends.cudnn.allow_tf32 = True
See https://github.com/pyannote/pyannote-audio/issues/1370 for more details.

  warnings.warn(
/home/bilguun/projects/work/monsum/monsum-speech/.venv/lib/python3.12/site-packages/pyannote/audio/models/blocks/pooling.py:103: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1839.)
  std = sequences.std(dim=-1, correction=1)
2026-11-01T17:30:21.641026Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=3 num_segments=267 request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 service_name=monsum-speech trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4
2026-11-01T17:30:21.863943Z [info     ] request.completed              audio_seconds=2785.25 diarize=True dropped=4 duration_ms=160276.7 endpoint=/v1/audio/transcriptions enhance=False file_ext=.wav language=mn method=POST model=models/ct2-whisper-large-v3-turbo-mn-1 queue_wait_ms=0 request_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 rtf=0.057 segments=211 service_name=monsum-speech size_bytes=89128046 status_code=200 trace_id=6fb6dae9-e985-4f9a-bd70-81367dfd54e4 vad=True vad_backend=silero words=8059
2026-11-01T17:30:21.864252Z [info     ] 127.0.0.1:53408 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:30:23.576590Z [info     ] asr_language_detected          detected_language=kk diverted=False endpoint=/v1/audio/transcriptions probability=0.1968994140625 request_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b service_name=monsum-speech trace_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b
2026-11-01T17:30:23.576866Z [info     ] Processing audio with duration 01:00:09.620 endpoint=/v1/audio/transcriptions request_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b service_name=monsum-speech trace_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b
2026-11-01T17:30:28.169149Z [info     ] VAD filter removed 04:57.984 of audio endpoint=/v1/audio/transcriptions request_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b service_name=monsum-speech trace_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b
2026-11-01T17:32:02.895119Z [info     ] transcription_completed        audio_seconds=3609.62 elapsed_ms=99318 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=249 num_words=10213 request_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b service_name=monsum-speech trace_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b
2026-11-01T17:33:34.676156Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=4 num_segments=1428 request_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b service_name=monsum-speech trace_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b
2026-11-01T17:33:36.105576Z [info     ] request.completed              audio_seconds=3609.62 diarize=True dropped=0 duration_ms=193725.68 endpoint=/v1/audio/transcriptions enhance=False file_ext=.wav language=mn method=POST model=models/ct2-whisper-large-v3-turbo-mn-1 queue_wait_ms=0 request_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b rtf=0.053 segments=249 service_name=monsum-speech size_bytes=115507886 status_code=200 trace_id=8f6f203c-d82f-4dd8-b0e0-9b69dd5ff72b vad=True vad_backend=silero words=10213
2026-11-01T17:33:36.105815Z [info     ] 127.0.0.1:53408 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:33:37.324785Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 service_name=monsum-speech trace_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8
2026-11-01T17:33:37.324930Z [info     ] Processing audio with duration 01:00:24.390 endpoint=/v1/audio/transcriptions request_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 service_name=monsum-speech trace_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8
2026-11-01T17:33:41.761319Z [info     ] VAD filter removed 23:55.096 of audio endpoint=/v1/audio/transcriptions request_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 service_name=monsum-speech trace_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8
2026-11-01T17:34:27.671800Z [info     ] transcription_completed        audio_seconds=3624.39 elapsed_ms=50347 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=52 num_segments=117 num_words=1677 request_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 service_name=monsum-speech trace_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8
2026-11-01T17:36:00.865584Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=21 num_segments=1054 request_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 service_name=monsum-speech trace_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8
2026-11-01T17:36:01.045111Z [info     ] request.completed              audio_seconds=3624.39 diarize=True dropped=52 duration_ms=144623.99 endpoint=/v1/audio/transcriptions enhance=False file_ext=.wav language=en method=POST model=models/ct2-whisper-large-v3-turbo queue_wait_ms=0 request_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 rtf=0.04 segments=117 service_name=monsum-speech size_bytes=115980526 status_code=200 trace_id=e1952942-c6e4-4561-8dd6-2bad5d0ab6b8 vad=True vad_backend=silero words=1677
2026-11-01T17:36:01.045285Z [info     ] 127.0.0.1:53408 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:36:01.745046Z [info     ] asr_language_detected          detected_language=bo diverted=False endpoint=/v1/audio/transcriptions probability=0.18115234375 request_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 service_name=monsum-speech trace_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0
2026-11-01T17:36:01.745185Z [info     ] Processing audio with duration 31:30.890 endpoint=/v1/audio/transcriptions request_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 service_name=monsum-speech trace_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0
2026-11-01T17:36:03.856861Z [info     ] VAD filter removed 04:36.568 of audio endpoint=/v1/audio/transcriptions request_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 service_name=monsum-speech trace_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0
2026-11-01T17:36:48.573429Z [info     ] transcription_completed        audio_seconds=1890.89 elapsed_ms=46828 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=120 num_words=4832 request_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 service_name=monsum-speech trace_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0
2026-11-01T17:37:36.726095Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=7 num_segments=943 request_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 service_name=monsum-speech trace_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0
2026-11-01T17:37:37.154568Z [info     ] request.completed              audio_seconds=1890.89 diarize=True dropped=0 duration_ms=96068.13 endpoint=/v1/audio/transcriptions enhance=False file_ext=.wav language=mn method=POST model=models/ct2-whisper-large-v3-turbo-mn-1 queue_wait_ms=0 request_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 rtf=0.05 segments=120 service_name=monsum-speech size_bytes=60508526 status_code=200 trace_id=65bc163f-6ea6-49a7-9e0d-1dd8cb0c68d0 vad=True vad_backend=silero words=4832
2026-11-01T17:37:37.154770Z [info     ] 127.0.0.1:53408 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:37:38.137101Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=ac2f5970-3a34-4d3a-9064-550f24f941ec service_name=monsum-speech trace_id=ac2f5970-3a34-4d3a-9064-550f24f941ec
2026-11-01T17:37:38.137275Z [info     ] Processing audio with duration 01:00:39.210 endpoint=/v1/audio/transcriptions request_id=ac2f5970-3a34-4d3a-9064-550f24f941ec service_name=monsum-speech trace_id=ac2f5970-3a34-4d3a-9064-550f24f941ec
2026-11-01T17:37:42.500153Z [info     ] VAD filter removed 11:44.760 of audio endpoint=/v1/audio/transcriptions request_id=ac2f5970-3a34-4d3a-9064-550f24f941ec service_name=monsum-speech trace_id=ac2f5970-3a34-4d3a-9064-550f24f941ec
2026-11-01T17:38:44.488230Z [info     ] transcription_completed        audio_seconds=3639.21 elapsed_ms=66351 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=79 num_segments=147 num_words=2460 request_id=ac2f5970-3a34-4d3a-9064-550f24f941ec service_name=monsum-speech trace_id=ac2f5970-3a34-4d3a-9064-550f24f941ec
2026-11-01T17:40:17.902028Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=20 num_segments=1323 request_id=ac2f5970-3a34-4d3a-9064-550f24f941ec service_name=monsum-speech trace_id=ac2f5970-3a34-4d3a-9064-550f24f941ec
2026-11-01T17:40:18.298981Z [info     ] request.completed              audio_seconds=3639.21 diarize=True dropped=79 duration_ms=161064.52 endpoint=/v1/audio/transcriptions enhance=False file_ext=.wav language=en method=POST model=models/ct2-whisper-large-v3-turbo queue_wait_ms=0 request_id=ac2f5970-3a34-4d3a-9064-550f24f941ec rtf=0.044 segments=147 service_name=monsum-speech size_bytes=116454766 status_code=200 trace_id=ac2f5970-3a34-4d3a-9064-550f24f941ec vad=True vad_backend=silero words=2460
2026-11-01T17:40:18.299156Z [info     ] 127.0.0.1:53408 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:40:20.189436Z [info     ] asr_language_detected          detected_language=en diverted=False endpoint=/v1/audio/transcriptions probability=0.358154296875 request_id=a4597521-d0c1-4f98-8e5b-7b9566490183 service_name=monsum-speech trace_id=a4597521-d0c1-4f98-8e5b-7b9566490183
2026-11-01T17:40:20.189589Z [info     ] Processing audio with duration 01:30:49.010 endpoint=/v1/audio/transcriptions request_id=a4597521-d0c1-4f98-8e5b-7b9566490183 service_name=monsum-speech trace_id=a4597521-d0c1-4f98-8e5b-7b9566490183
2026-11-01T17:40:27.231959Z [info     ] VAD filter removed 12:34.600 of audio endpoint=/v1/audio/transcriptions request_id=a4597521-d0c1-4f98-8e5b-7b9566490183 service_name=monsum-speech trace_id=a4597521-d0c1-4f98-8e5b-7b9566490183
2026-11-01T17:41:41.723320Z [info     ] Shutting down                  service_name=monsum-speech
2026-11-01T17:41:41.824010Z [info     ] Waiting for background tasks to complete. (CTRL+C to force quit) service_name=monsum-speech