2026-11-01T16:33:05.475714Z [info     ] Started server process [2663248] service_name=monsum-speech
2026-11-01T16:33:05.475811Z [info     ] Waiting for application startup. service_name=monsum-speech
2026-11-01T16:33:05.475941Z [info     ] Application startup complete.  service_name=monsum-speech
2026-11-01T16:33:05.476547Z [info     ] Uvicorn running on http://127.0.0.1:8012 (Press CTRL+C to quit) service_name=monsum-speech
2026-11-01T16:33:10.209055Z [info     ] request.completed              duration_ms=3.85 endpoint=/health method=GET request_id=3a295805-1ebd-4185-8953-60230b2baee8 service_name=monsum-speech status_code=200 trace_id=3a295805-1ebd-4185-8953-60230b2baee8
2026-11-01T16:33:10.209474Z [info     ] 127.0.0.1:52146 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:33:10.228201Z [info     ] request.completed              duration_ms=0.69 endpoint=/health method=GET request_id=6d7e0355-611d-4c73-bb9e-9ef688f1c947 service_name=monsum-speech status_code=200 trace_id=6d7e0355-611d-4c73-bb9e-9ef688f1c947
2026-11-01T16:33:10.228707Z [info     ] 127.0.0.1:52160 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:33:12.525305Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
2026-11-01T16:33:13.746581Z [info     ] asr_language_detected          detected_language=bo diverted=False endpoint=/v1/audio/transcriptions probability=0.18115234375 request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
2026-11-01T16:33:13.746705Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo-mn-1 request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
2026-11-01T16:33:14.406776Z [info     ] Processing audio with duration 31:30.890 endpoint=/v1/audio/transcriptions request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
2026-11-01T16:33:16.687138Z [info     ] VAD filter removed 04:36.568 of audio endpoint=/v1/audio/transcriptions request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
2026-11-01T16:34:01.239527Z [info     ] transcription_completed        audio_seconds=1890.89 elapsed_ms=47493 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=120 num_words=4832 request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
/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(
2026-11-01T16:34:02.874172Z [info     ] diarization_pipeline_loading   device=cuda endpoint=/v1/audio/transcriptions path=models/speaker-diarization-community-1 request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
/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)
2026-11-01T16:34:51.888745Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=7 num_segments=998 request_id=30cfe941-cc42-4e92-b674-954934b47112 service_name=monsum-speech trace_id=30cfe941-cc42-4e92-b674-954934b47112
2026-11-01T16:34:52.342899Z [info     ] request.completed              audio_seconds=1890.89 diarize=True dropped=0 duration_ms=101118.9 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=30cfe941-cc42-4e92-b674-954934b47112 rtf=0.053 segments=120 service_name=monsum-speech size_bytes=60508526 status_code=200 trace_id=30cfe941-cc42-4e92-b674-954934b47112 vad=True vad_backend=silero words=4832
2026-11-01T16:34:52.343085Z [info     ] 127.0.0.1:45660 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:34:53.594818Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=5aed38d0-176c-457a-9f44-3f05c976c489 service_name=monsum-speech trace_id=5aed38d0-176c-457a-9f44-3f05c976c489
2026-11-01T16:34:53.595106Z [info     ] Processing audio with duration 01:00:39.210 endpoint=/v1/audio/transcriptions request_id=5aed38d0-176c-457a-9f44-3f05c976c489 service_name=monsum-speech trace_id=5aed38d0-176c-457a-9f44-3f05c976c489
2026-11-01T16:34:58.061753Z [info     ] VAD filter removed 11:44.760 of audio endpoint=/v1/audio/transcriptions request_id=5aed38d0-176c-457a-9f44-3f05c976c489 service_name=monsum-speech trace_id=5aed38d0-176c-457a-9f44-3f05c976c489
2026-11-01T16:36:01.012769Z [info     ] transcription_completed        audio_seconds=3639.21 elapsed_ms=67418 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=0 num_segments=226 num_words=5001 request_id=5aed38d0-176c-457a-9f44-3f05c976c489 service_name=monsum-speech trace_id=5aed38d0-176c-457a-9f44-3f05c976c489
2026-11-01T16:37:37.134100Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=20 num_segments=1329 request_id=5aed38d0-176c-457a-9f44-3f05c976c489 service_name=monsum-speech trace_id=5aed38d0-176c-457a-9f44-3f05c976c489
2026-11-01T16:37:37.970933Z [info     ] request.completed              audio_seconds=3639.21 diarize=True dropped=0 duration_ms=165506.5 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=5aed38d0-176c-457a-9f44-3f05c976c489 rtf=0.045 segments=226 service_name=monsum-speech size_bytes=116454766 status_code=200 trace_id=5aed38d0-176c-457a-9f44-3f05c976c489 vad=True vad_backend=silero words=5001
2026-11-01T16:37:37.971102Z [info     ] 127.0.0.1:45660 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:37:40.024754Z [info     ] asr_language_detected          detected_language=en diverted=False endpoint=/v1/audio/transcriptions probability=0.358154296875 request_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c service_name=monsum-speech trace_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c
2026-11-01T16:37:40.025035Z [info     ] Processing audio with duration 01:30:49.010 endpoint=/v1/audio/transcriptions request_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c service_name=monsum-speech trace_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c
2026-11-01T16:37:46.972131Z [info     ] VAD filter removed 12:34.600 of audio endpoint=/v1/audio/transcriptions request_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c service_name=monsum-speech trace_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c
2026-11-01T16:40:00.846888Z [info     ] transcription_completed        audio_seconds=5449.01 elapsed_ms=140822 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=352 num_words=14391 request_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c service_name=monsum-speech trace_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c
2026-11-01T16:42:23.052614Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=10 num_segments=3148 request_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c service_name=monsum-speech trace_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c
2026-11-01T16:42:27.007795Z [info     ] request.completed              audio_seconds=5449.01 diarize=True dropped=0 duration_ms=288951.69 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=4efacd9f-0a36-4cff-83f2-9924b2107d6c rtf=0.052 segments=352 service_name=monsum-speech size_bytes=174368366 status_code=200 trace_id=4efacd9f-0a36-4cff-83f2-9924b2107d6c vad=True vad_backend=silero words=14391
2026-11-01T16:42:27.008018Z [info     ] 127.0.0.1:45660 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:42:28.745343Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=24650d42-1dcd-448c-b885-b1cbab1fb78e service_name=monsum-speech trace_id=24650d42-1dcd-448c-b885-b1cbab1fb78e
2026-11-01T16:42:28.745494Z [info     ] Processing audio with duration 01:33:50.680 endpoint=/v1/audio/transcriptions request_id=24650d42-1dcd-448c-b885-b1cbab1fb78e service_name=monsum-speech trace_id=24650d42-1dcd-448c-b885-b1cbab1fb78e
2026-11-01T16:42:35.736905Z [info     ] VAD filter removed 43:25.992 of audio endpoint=/v1/audio/transcriptions request_id=24650d42-1dcd-448c-b885-b1cbab1fb78e service_name=monsum-speech trace_id=24650d42-1dcd-448c-b885-b1cbab1fb78e
2026-11-01T16:43:39.828509Z [info     ] transcription_completed        audio_seconds=5630.68 elapsed_ms=71083 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=0 num_segments=228 num_words=3941 request_id=24650d42-1dcd-448c-b885-b1cbab1fb78e service_name=monsum-speech trace_id=24650d42-1dcd-448c-b885-b1cbab1fb78e
2026-11-01T16:46:03.684814Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=12 num_segments=1379 request_id=24650d42-1dcd-448c-b885-b1cbab1fb78e service_name=monsum-speech trace_id=24650d42-1dcd-448c-b885-b1cbab1fb78e
2026-11-01T16:46:04.365593Z [info     ] request.completed              audio_seconds=5630.68 diarize=True dropped=0 duration_ms=216865.16 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=24650d42-1dcd-448c-b885-b1cbab1fb78e rtf=0.038 segments=228 service_name=monsum-speech size_bytes=180181806 status_code=200 trace_id=24650d42-1dcd-448c-b885-b1cbab1fb78e vad=True vad_backend=silero words=3941
2026-11-01T16:46:04.365747Z [info     ] 127.0.0.1:45660 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:46:05.389532Z [info     ] asr_language_detected          detected_language=bo diverted=False endpoint=/v1/audio/transcriptions probability=0.24560546875 request_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da service_name=monsum-speech trace_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da
2026-11-01T16:46:05.389720Z [info     ] Processing audio with duration 57:25.920 endpoint=/v1/audio/transcriptions request_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da service_name=monsum-speech trace_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da
2026-11-01T16:46:09.706471Z [info     ] VAD filter removed 03:45.432 of audio endpoint=/v1/audio/transcriptions request_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da service_name=monsum-speech trace_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da
2026-11-01T16:47:43.459140Z [info     ] transcription_completed        audio_seconds=3445.92 elapsed_ms=98069 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=250 num_words=9410 request_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da service_name=monsum-speech trace_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da
2026-11-01T16:49:11.814851Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=8 num_segments=1472 request_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da service_name=monsum-speech trace_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da
2026-11-01T16:49:13.158312Z [info     ] request.completed              audio_seconds=3445.92 diarize=True dropped=0 duration_ms=188701.52 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=4f4e2d18-4d65-443f-bb86-e03a8a2491da rtf=0.054 segments=250 service_name=monsum-speech size_bytes=110269486 status_code=200 trace_id=4f4e2d18-4d65-443f-bb86-e03a8a2491da vad=True vad_backend=silero words=9410
2026-11-01T16:49:13.158495Z [info     ] 127.0.0.1:45660 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T16:49:13.459825Z [info     ] Shutting down                  service_name=monsum-speech
2026-11-01T16:49:13.561082Z [info     ] Waiting for application shutdown. service_name=monsum-speech
2026-11-01T16:49:13.561644Z [info     ] Application shutdown complete. service_name=monsum-speech
2026-11-01T16:49:13.561929Z [info     ] Finished server process [2663248] service_name=monsum-speech