2026-11-01T18:02:08.117364Z [info     ] Started server process [2855368] service_name=monsum-speech
2026-11-01T18:02:08.117477Z [info     ] Waiting for application startup. service_name=monsum-speech
2026-11-01T18:02:08.117612Z [info     ] Application startup complete.  service_name=monsum-speech
2026-11-01T18:02:08.118295Z [info     ] Uvicorn running on http://127.0.0.1:8012 (Press CTRL+C to quit) service_name=monsum-speech
2026-11-01T18:02:12.829979Z [info     ] request.completed              duration_ms=0.78 endpoint=/health method=GET request_id=0f488233-8d7e-46a0-8701-3930b6e3356f service_name=monsum-speech status_code=200 trace_id=0f488233-8d7e-46a0-8701-3930b6e3356f
2026-11-01T18:02:12.830107Z [info     ] 127.0.0.1:55350 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:02:12.839136Z [info     ] request.completed              duration_ms=0.3 endpoint=/health method=GET request_id=636af667-0395-4649-a6ee-4d9103f7db3d service_name=monsum-speech status_code=200 trace_id=636af667-0395-4649-a6ee-4d9103f7db3d
2026-11-01T18:02:12.839371Z [info     ] 127.0.0.1:55356 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:02:14.381146Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
2026-11-01T18:02:15.414312Z [info     ] asr_language_detected          detected_language=kk diverted=False endpoint=/v1/audio/transcriptions probability=0.1790771484375 request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
2026-11-01T18:02:15.414429Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo-mn-1 request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
2026-11-01T18:02:15.851484Z [info     ] Processing audio with duration 46:25.250 endpoint=/v1/audio/transcriptions request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
2026-11-01T18:02:19.045933Z [info     ] VAD filter removed 02:54.392 of audio endpoint=/v1/audio/transcriptions request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
2026-11-01T18:03:39.581790Z [info     ] transcription_completed        audio_seconds=2785.25 elapsed_ms=84167 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=215 num_words=8220 request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
/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(
2026-11-01T18:03:41.013908Z [info     ] diarization_pipeline_loading   device=cuda endpoint=/v1/audio/transcriptions path=models/speaker-diarization-community-1 request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
/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)
2026-11-01T18:04:52.415911Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=3 num_segments=308 request_id=17353a76-d5f3-41a5-bd8c-98794888ac65 service_name=monsum-speech trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65
2026-11-01T18:04:52.687741Z [info     ] request.completed              audio_seconds=2785.25 diarize=True dropped=0 duration_ms=159627.59 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=17353a76-d5f3-41a5-bd8c-98794888ac65 rtf=0.057 segments=215 service_name=monsum-speech size_bytes=89128046 status_code=200 trace_id=17353a76-d5f3-41a5-bd8c-98794888ac65 vad=True vad_backend=silero words=8220
2026-11-01T18:04:52.688016Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:04:54.064991Z [info     ] asr_language_detected          detected_language=kk diverted=False endpoint=/v1/audio/transcriptions probability=0.1968994140625 request_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c service_name=monsum-speech trace_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c
2026-11-01T18:04:54.065274Z [info     ] Processing audio with duration 01:00:09.620 endpoint=/v1/audio/transcriptions request_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c service_name=monsum-speech trace_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c
2026-11-01T18:04:58.139055Z [info     ] VAD filter removed 04:57.984 of audio endpoint=/v1/audio/transcriptions request_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c service_name=monsum-speech trace_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c
2026-11-01T18:06:32.948596Z [info     ] transcription_completed        audio_seconds=3609.62 elapsed_ms=98883 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=249 num_words=10213 request_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c service_name=monsum-speech trace_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c
2026-11-01T18:08:04.798450Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=4 num_segments=1442 request_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c service_name=monsum-speech trace_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c
2026-11-01T18:08:06.266392Z [info     ] request.completed              audio_seconds=3609.62 diarize=True dropped=0 duration_ms=193093.07 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=665802ec-facc-42f4-b5f2-cb0d2e40b62c rtf=0.053 segments=249 service_name=monsum-speech size_bytes=115507886 status_code=200 trace_id=665802ec-facc-42f4-b5f2-cb0d2e40b62c vad=True vad_backend=silero words=10213
2026-11-01T18:08:06.266599Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:08:07.461165Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=b572c322-b77f-43fb-b5b5-ace587f93dff service_name=monsum-speech trace_id=b572c322-b77f-43fb-b5b5-ace587f93dff
2026-11-01T18:08:07.461316Z [info     ] Processing audio with duration 01:00:24.390 endpoint=/v1/audio/transcriptions request_id=b572c322-b77f-43fb-b5b5-ace587f93dff service_name=monsum-speech trace_id=b572c322-b77f-43fb-b5b5-ace587f93dff
2026-11-01T18:08:11.631590Z [info     ] VAD filter removed 23:55.096 of audio endpoint=/v1/audio/transcriptions request_id=b572c322-b77f-43fb-b5b5-ace587f93dff service_name=monsum-speech trace_id=b572c322-b77f-43fb-b5b5-ace587f93dff
2026-11-01T18:08:57.539734Z [info     ] transcription_completed        audio_seconds=3624.39 elapsed_ms=50078 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=0 num_segments=169 num_words=3458 request_id=b572c322-b77f-43fb-b5b5-ace587f93dff service_name=monsum-speech trace_id=b572c322-b77f-43fb-b5b5-ace587f93dff
2026-11-01T18:10:31.020776Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=20 num_segments=1095 request_id=b572c322-b77f-43fb-b5b5-ace587f93dff service_name=monsum-speech trace_id=b572c322-b77f-43fb-b5b5-ace587f93dff
2026-11-01T18:10:31.436455Z [info     ] request.completed              audio_seconds=3624.39 diarize=True dropped=0 duration_ms=144859.72 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=b572c322-b77f-43fb-b5b5-ace587f93dff rtf=0.04 segments=169 service_name=monsum-speech size_bytes=115980526 status_code=200 trace_id=b572c322-b77f-43fb-b5b5-ace587f93dff vad=True vad_backend=silero words=3458
2026-11-01T18:10:31.436665Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:10:32.140590Z [info     ] asr_language_detected          detected_language=bo diverted=False endpoint=/v1/audio/transcriptions probability=0.18115234375 request_id=a9c988e9-991c-4712-8bbb-b7db3823a201 service_name=monsum-speech trace_id=a9c988e9-991c-4712-8bbb-b7db3823a201
2026-11-01T18:10:32.140764Z [info     ] Processing audio with duration 31:30.890 endpoint=/v1/audio/transcriptions request_id=a9c988e9-991c-4712-8bbb-b7db3823a201 service_name=monsum-speech trace_id=a9c988e9-991c-4712-8bbb-b7db3823a201
2026-11-01T18:10:34.346217Z [info     ] VAD filter removed 04:36.568 of audio endpoint=/v1/audio/transcriptions request_id=a9c988e9-991c-4712-8bbb-b7db3823a201 service_name=monsum-speech trace_id=a9c988e9-991c-4712-8bbb-b7db3823a201
2026-11-01T18:11:19.080913Z [info     ] transcription_completed        audio_seconds=1890.89 elapsed_ms=46940 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=120 num_words=4832 request_id=a9c988e9-991c-4712-8bbb-b7db3823a201 service_name=monsum-speech trace_id=a9c988e9-991c-4712-8bbb-b7db3823a201
2026-11-01T18:12:07.479517Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=7 num_segments=998 request_id=a9c988e9-991c-4712-8bbb-b7db3823a201 service_name=monsum-speech trace_id=a9c988e9-991c-4712-8bbb-b7db3823a201
2026-11-01T18:12:07.940033Z [info     ] request.completed              audio_seconds=1890.89 diarize=True dropped=0 duration_ms=96455.88 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=a9c988e9-991c-4712-8bbb-b7db3823a201 rtf=0.051 segments=120 service_name=monsum-speech size_bytes=60508526 status_code=200 trace_id=a9c988e9-991c-4712-8bbb-b7db3823a201 vad=True vad_backend=silero words=4832
2026-11-01T18:12:07.940217Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:12:08.913409Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e service_name=monsum-speech trace_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e
2026-11-01T18:12:08.913603Z [info     ] Processing audio with duration 01:00:39.210 endpoint=/v1/audio/transcriptions request_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e service_name=monsum-speech trace_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e
2026-11-01T18:12:13.103328Z [info     ] VAD filter removed 11:44.760 of audio endpoint=/v1/audio/transcriptions request_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e service_name=monsum-speech trace_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e
2026-11-01T18:13:15.103380Z [info     ] transcription_completed        audio_seconds=3639.21 elapsed_ms=66190 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=0 num_segments=226 num_words=5001 request_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e service_name=monsum-speech trace_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e
2026-11-01T18:14:48.869794Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=20 num_segments=1345 request_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e service_name=monsum-speech trace_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e
2026-11-01T18:14:49.704848Z [info     ] request.completed              audio_seconds=3639.21 diarize=True dropped=0 duration_ms=161681.37 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=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e rtf=0.044 segments=226 service_name=monsum-speech size_bytes=116454766 status_code=200 trace_id=01cb1a9b-a8b7-4e73-a3bb-b9bdabd92e6e vad=True vad_backend=silero words=5001
2026-11-01T18:14:49.705034Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:14:50.929089Z [info     ] asr_language_detected          detected_language=en diverted=False endpoint=/v1/audio/transcriptions probability=0.358154296875 request_id=226404d5-e45a-49f8-b26f-539a7ae50e44 service_name=monsum-speech trace_id=226404d5-e45a-49f8-b26f-539a7ae50e44
2026-11-01T18:14:50.929244Z [info     ] Processing audio with duration 01:30:49.010 endpoint=/v1/audio/transcriptions request_id=226404d5-e45a-49f8-b26f-539a7ae50e44 service_name=monsum-speech trace_id=226404d5-e45a-49f8-b26f-539a7ae50e44
2026-11-01T18:14:57.555736Z [info     ] VAD filter removed 12:34.600 of audio endpoint=/v1/audio/transcriptions request_id=226404d5-e45a-49f8-b26f-539a7ae50e44 service_name=monsum-speech trace_id=226404d5-e45a-49f8-b26f-539a7ae50e44
2026-11-01T18:17:08.438908Z [info     ] transcription_completed        audio_seconds=5449.01 elapsed_ms=137510 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=352 num_words=14391 request_id=226404d5-e45a-49f8-b26f-539a7ae50e44 service_name=monsum-speech trace_id=226404d5-e45a-49f8-b26f-539a7ae50e44
2026-11-01T18:19:31.568928Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=10 num_segments=3082 request_id=226404d5-e45a-49f8-b26f-539a7ae50e44 service_name=monsum-speech trace_id=226404d5-e45a-49f8-b26f-539a7ae50e44
2026-11-01T18:19:35.589755Z [info     ] request.completed              audio_seconds=5449.01 diarize=True dropped=0 duration_ms=285833.71 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=226404d5-e45a-49f8-b26f-539a7ae50e44 rtf=0.052 segments=352 service_name=monsum-speech size_bytes=174368366 status_code=200 trace_id=226404d5-e45a-49f8-b26f-539a7ae50e44 vad=True vad_backend=silero words=14391
2026-11-01T18:19:35.589967Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:19:37.199546Z [info     ] asr_language_detected          detected_language=en diverted=True endpoint=/v1/audio/transcriptions probability=0.51416015625 request_id=a256edf9-5422-4b54-9054-396c18fd6a9a service_name=monsum-speech trace_id=a256edf9-5422-4b54-9054-396c18fd6a9a
2026-11-01T18:19:37.199696Z [info     ] Processing audio with duration 01:33:50.680 endpoint=/v1/audio/transcriptions request_id=a256edf9-5422-4b54-9054-396c18fd6a9a service_name=monsum-speech trace_id=a256edf9-5422-4b54-9054-396c18fd6a9a
2026-11-01T18:19:44.420325Z [info     ] VAD filter removed 43:25.992 of audio endpoint=/v1/audio/transcriptions request_id=a256edf9-5422-4b54-9054-396c18fd6a9a service_name=monsum-speech trace_id=a256edf9-5422-4b54-9054-396c18fd6a9a
2026-11-01T18:20:48.535445Z [info     ] transcription_completed        audio_seconds=5630.68 elapsed_ms=71336 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo num_dropped=0 num_segments=228 num_words=3941 request_id=a256edf9-5422-4b54-9054-396c18fd6a9a service_name=monsum-speech trace_id=a256edf9-5422-4b54-9054-396c18fd6a9a
2026-11-01T18:23:12.568953Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=14 num_segments=1448 request_id=a256edf9-5422-4b54-9054-396c18fd6a9a service_name=monsum-speech trace_id=a256edf9-5422-4b54-9054-396c18fd6a9a
2026-11-01T18:23:13.259331Z [info     ] request.completed              audio_seconds=5630.68 diarize=True dropped=0 duration_ms=217225.7 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=a256edf9-5422-4b54-9054-396c18fd6a9a rtf=0.038 segments=228 service_name=monsum-speech size_bytes=180181806 status_code=200 trace_id=a256edf9-5422-4b54-9054-396c18fd6a9a vad=True vad_backend=silero words=3941
2026-11-01T18:23:13.259540Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:23:14.200324Z [info     ] asr_language_detected          detected_language=bo diverted=False endpoint=/v1/audio/transcriptions probability=0.24560546875 request_id=344332e8-a3a2-4133-b421-cffd363af28e service_name=monsum-speech trace_id=344332e8-a3a2-4133-b421-cffd363af28e
2026-11-01T18:23:14.200466Z [info     ] Processing audio with duration 57:25.920 endpoint=/v1/audio/transcriptions request_id=344332e8-a3a2-4133-b421-cffd363af28e service_name=monsum-speech trace_id=344332e8-a3a2-4133-b421-cffd363af28e
2026-11-01T18:23:18.199524Z [info     ] VAD filter removed 03:45.432 of audio endpoint=/v1/audio/transcriptions request_id=344332e8-a3a2-4133-b421-cffd363af28e service_name=monsum-speech trace_id=344332e8-a3a2-4133-b421-cffd363af28e
2026-11-01T18:24:51.221561Z [info     ] transcription_completed        audio_seconds=3445.92 elapsed_ms=97021 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=250 num_words=9410 request_id=344332e8-a3a2-4133-b421-cffd363af28e service_name=monsum-speech trace_id=344332e8-a3a2-4133-b421-cffd363af28e
2026-11-01T18:26:19.301930Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=9 num_segments=1476 request_id=344332e8-a3a2-4133-b421-cffd363af28e service_name=monsum-speech trace_id=344332e8-a3a2-4133-b421-cffd363af28e
2026-11-01T18:26:20.665113Z [info     ] request.completed              audio_seconds=3445.92 diarize=True dropped=0 duration_ms=187356.31 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=344332e8-a3a2-4133-b421-cffd363af28e rtf=0.054 segments=250 service_name=monsum-speech size_bytes=110269486 status_code=200 trace_id=344332e8-a3a2-4133-b421-cffd363af28e vad=True vad_backend=silero words=9410
2026-11-01T18:26:20.665299Z [info     ] 127.0.0.1:55358 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T18:26:20.966030Z [info     ] Shutting down                  service_name=monsum-speech
2026-11-01T18:26:21.065981Z [info     ] Waiting for application shutdown. service_name=monsum-speech
2026-11-01T18:26:21.066490Z [info     ] Application shutdown complete. service_name=monsum-speech
2026-11-01T18:26:21.066731Z [info     ] Finished server process [2855368] service_name=monsum-speech