2026-11-01T17:50:08.215197Z [info     ] Started server process [2839365] service_name=monsum-speech
2026-11-01T17:50:08.215292Z [info     ] Waiting for application startup. service_name=monsum-speech
2026-11-01T17:50:08.215432Z [info     ] Application startup complete.  service_name=monsum-speech
2026-11-01T17:50:08.216077Z [info     ] Uvicorn running on http://127.0.0.1:8012 (Press CTRL+C to quit) service_name=monsum-speech
2026-11-01T17:50:12.933985Z [info     ] request.completed              duration_ms=0.74 endpoint=/health method=GET request_id=e74eb273-0bff-41e7-b9f8-d9f4da9cb87b service_name=monsum-speech status_code=200 trace_id=e74eb273-0bff-41e7-b9f8-d9f4da9cb87b
2026-11-01T17:50:12.934102Z [info     ] 127.0.0.1:40228 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:50:12.950867Z [info     ] request.completed              duration_ms=0.71 endpoint=/health method=GET request_id=131db47d-334f-43f8-9714-58796a43e5f0 service_name=monsum-speech status_code=200 trace_id=131db47d-334f-43f8-9714-58796a43e5f0
2026-11-01T17:50:12.951331Z [info     ] 127.0.0.1:40244 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:50:14.434832Z [info     ] decode_cache_hit               digest=31b58ea8baa1 endpoint=/v1/audio/transcriptions request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff samples=87184161 service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:50:15.271506Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:50:16.306018Z [info     ] asr_language_detected          detected_language=en diverted=False endpoint=/v1/audio/transcriptions probability=0.358154296875 request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:50:16.306132Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo-mn-1 request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:50:16.868161Z [info     ] Processing audio with duration 01:30:49.010 endpoint=/v1/audio/transcriptions request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:50:23.563986Z [info     ] VAD filter removed 12:34.600 of audio endpoint=/v1/audio/transcriptions request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:52:34.149592Z [info     ] transcription_completed        audio_seconds=5449.01 elapsed_ms=137843 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=3 num_segments=349 num_words=14243 request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
/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(
2026-11-01T17:52:35.640693Z [info     ] diarization_pipeline_loading   device=cuda endpoint=/v1/audio/transcriptions path=models/speaker-diarization-community-1 request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
/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)
2026-11-01T17:54:58.284579Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=10 num_segments=3148 request_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff service_name=monsum-speech trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff
2026-11-01T17:55:02.299473Z [info     ] request.completed              audio_seconds=5449.01 diarize=True dropped=3 duration_ms=288256.01 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=2a2fb70d-07e1-4c59-886c-c535cd1816ff rtf=0.052 segments=349 service_name=monsum-speech size_bytes=174368366 status_code=200 trace_id=2a2fb70d-07e1-4c59-886c-c535cd1816ff vad=True vad_backend=silero words=14243
2026-11-01T17:55:02.299754Z [info     ] 127.0.0.1:40246 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:55:04.442448Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d service_name=monsum-speech trace_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d
2026-11-01T17:55:04.442720Z [info     ] Processing audio with duration 01:33:50.680 endpoint=/v1/audio/transcriptions request_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d service_name=monsum-speech trace_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d
2026-11-01T17:55:12.196353Z [info     ] VAD filter removed 43:25.992 of audio endpoint=/v1/audio/transcriptions request_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d service_name=monsum-speech trace_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d
2026-11-01T17:56:16.297068Z [info     ] transcription_completed        audio_seconds=5630.68 elapsed_ms=71855 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=51 num_segments=177 num_words=2342 request_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d service_name=monsum-speech trace_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d
2026-11-01T17:58:39.762199Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=12 num_segments=1379 request_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d service_name=monsum-speech trace_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d
2026-11-01T17:58:40.177291Z [info     ] request.completed              audio_seconds=5630.68 diarize=True dropped=51 duration_ms=217444.53 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=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d rtf=0.038 segments=177 service_name=monsum-speech size_bytes=180181806 status_code=200 trace_id=b62ebb8c-de40-4045-ad9e-aeb5f6a4439d vad=True vad_backend=silero words=2342
2026-11-01T17:58:40.177485Z [info     ] 127.0.0.1:40246 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T17:58:41.160956Z [info     ] asr_language_detected          detected_language=bo diverted=False endpoint=/v1/audio/transcriptions probability=0.24560546875 request_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8 service_name=monsum-speech trace_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8
2026-11-01T17:58:41.161111Z [info     ] Processing audio with duration 57:25.920 endpoint=/v1/audio/transcriptions request_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8 service_name=monsum-speech trace_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8
2026-11-01T17:58:45.175425Z [info     ] VAD filter removed 03:45.432 of audio endpoint=/v1/audio/transcriptions request_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8 service_name=monsum-speech trace_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8
2026-11-01T18:00:18.147061Z [info     ] transcription_completed        audio_seconds=3445.92 elapsed_ms=96986 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=5 num_segments=245 num_words=9179 request_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8 service_name=monsum-speech trace_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8
2026-11-01T18:01:46.187393Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=8 num_segments=1472 request_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8 service_name=monsum-speech trace_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8
2026-11-01T18:01:47.502652Z [info     ] request.completed              audio_seconds=3445.92 diarize=True dropped=5 duration_ms=187281.53 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=705195bb-334e-4c79-b75c-3ce52b9bb8d8 rtf=0.054 segments=245 service_name=monsum-speech size_bytes=110269486 status_code=200 trace_id=705195bb-334e-4c79-b75c-3ce52b9bb8d8 vad=True vad_backend=silero words=9179
2026-11-01T18:01:47.502848Z [info     ] 127.0.0.1:40246 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:01:47.803807Z [info     ] Shutting down                  service_name=monsum-speech
2026-11-01T18:01:47.904764Z [info     ] Waiting for application shutdown. service_name=monsum-speech
2026-11-01T18:01:47.905271Z [info     ] Application shutdown complete. service_name=monsum-speech
2026-11-01T18:01:47.905514Z [info     ] Finished server process [2839365] service_name=monsum-speech