2026-11-01T19:04:10.359361Z [info     ] Started server process [2935188] service_name=monsum-speech
2026-11-01T19:04:10.359454Z [info     ] Waiting for application startup. service_name=monsum-speech
2026-11-01T19:04:10.359594Z [info     ] Application startup complete.  service_name=monsum-speech
2026-11-01T19:04:10.360374Z [info     ] Uvicorn running on http://127.0.0.1:8012 (Press CTRL+C to quit) service_name=monsum-speech
2026-11-01T19:04:15.073365Z [info     ] request.completed              duration_ms=0.79 endpoint=/health method=GET request_id=bdd1c9ce-7e70-4dd0-84d2-6af4cebc1d27 service_name=monsum-speech status_code=200 trace_id=bdd1c9ce-7e70-4dd0-84d2-6af4cebc1d27
2026-11-01T19:04:15.073490Z [info     ] 127.0.0.1:59386 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:04:15.081846Z [info     ] request.completed              duration_ms=0.15 endpoint=/health method=GET request_id=9dd543f0-c074-4638-b56c-24a391116bfa service_name=monsum-speech status_code=200 trace_id=9dd543f0-c074-4638-b56c-24a391116bfa
2026-11-01T19:04:15.081947Z [info     ] 127.0.0.1:59396 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:04:17.176871Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=152 request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:04:17.181234Z [info     ] lid_model_loading              endpoint=/v1/audio/transcriptions path=models/ambernet-langid/ambernet.onnx request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:04:17.713239Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:04:17.840170Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo-mn-1 request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:04:18.356213Z [info     ] Processing audio with duration 46:25.250 endpoint=/v1/audio/transcriptions request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:04:21.608393Z [info     ] VAD filter removed 02:54.392 of audio endpoint=/v1/audio/transcriptions request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:05:42.100587Z [info     ] transcription_completed        audio_seconds=2785.25 elapsed_ms=84387 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=215 num_words=8220 request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
/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(
2026-11-01T19:05:43.616833Z [info     ] diarization_pipeline_loading   device=cuda endpoint=/v1/audio/transcriptions path=models/speaker-diarization-community-1 request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
/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)
2026-11-01T19:06:55.152872Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=3 num_segments=308 request_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 service_name=monsum-speech trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59
2026-11-01T19:06:55.420316Z [info     ] request.completed              audio_seconds=2785.25 diarize=True dropped=0 duration_ms=160127.31 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=afc4763d-7f9a-408c-a8f8-d38928ab0c59 rtf=0.057 segments=215 service_name=monsum-speech size_bytes=89128046 status_code=200 trace_id=afc4763d-7f9a-408c-a8f8-d38928ab0c59 vad=True vad_backend=silero words=8220
2026-11-01T19:06:55.420648Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:06:57.749339Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=221 request_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a service_name=monsum-speech trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a
2026-11-01T19:06:58.185702Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a service_name=monsum-speech trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a
2026-11-01T19:06:58.186150Z [info     ] Processing audio with duration 01:00:09.620 endpoint=/v1/audio/transcriptions request_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a service_name=monsum-speech trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a
2026-11-01T19:07:03.096976Z [info     ] VAD filter removed 04:57.984 of audio endpoint=/v1/audio/transcriptions request_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a service_name=monsum-speech trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a
2026-11-01T19:08:37.914534Z [info     ] transcription_completed        audio_seconds=3609.62 elapsed_ms=99729 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=249 num_words=10213 request_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a service_name=monsum-speech trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a
2026-11-01T19:10:10.037286Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=4 num_segments=1442 request_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a service_name=monsum-speech trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a
2026-11-01T19:10:11.501535Z [info     ] request.completed              audio_seconds=3609.62 diarize=True dropped=0 duration_ms=195561.02 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=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a rtf=0.053 segments=249 service_name=monsum-speech size_bytes=115507886 status_code=200 trace_id=36a906f7-e9a8-4bb8-9e0b-4474e28ea54a vad=True vad_backend=silero words=10213
2026-11-01T19:10:11.501739Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:10:13.437380Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=160 request_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 service_name=monsum-speech trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2
2026-11-01T19:10:13.869433Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=0.9999951124191284 request_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 service_name=monsum-speech trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2
2026-11-01T19:10:13.869616Z [info     ] Processing audio with duration 01:00:24.390 endpoint=/v1/audio/transcriptions request_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 service_name=monsum-speech trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2
2026-11-01T19:10:18.570256Z [info     ] VAD filter removed 23:55.096 of audio endpoint=/v1/audio/transcriptions request_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 service_name=monsum-speech trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2
2026-11-01T19:11:18.799034Z [info     ] transcription_completed        audio_seconds=3624.39 elapsed_ms=64929 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=169 num_words=5879 request_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 service_name=monsum-speech trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2
2026-11-01T19:12:52.584450Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=21 num_segments=1092 request_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 service_name=monsum-speech trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2
2026-11-01T19:12:53.163527Z [info     ] request.completed              audio_seconds=3624.39 diarize=True dropped=0 duration_ms=161343.95 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=314e2d6c-8af3-4787-b7d7-17c8809222a2 rtf=0.044 segments=169 service_name=monsum-speech size_bytes=115980526 status_code=200 trace_id=314e2d6c-8af3-4787-b7d7-17c8809222a2 vad=True vad_backend=silero words=5879
2026-11-01T19:12:53.163730Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:12:54.361102Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=208 request_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b service_name=monsum-speech trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b
2026-11-01T19:12:54.793997Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b service_name=monsum-speech trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b
2026-11-01T19:12:54.794178Z [info     ] Processing audio with duration 31:30.890 endpoint=/v1/audio/transcriptions request_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b service_name=monsum-speech trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b
2026-11-01T19:12:57.041542Z [info     ] VAD filter removed 04:36.568 of audio endpoint=/v1/audio/transcriptions request_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b service_name=monsum-speech trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b
2026-11-01T19:13:41.812132Z [info     ] transcription_completed        audio_seconds=1890.89 elapsed_ms=47018 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=120 num_words=4832 request_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b service_name=monsum-speech trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b
2026-11-01T19:14:30.149524Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=7 num_segments=998 request_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b service_name=monsum-speech trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b
2026-11-01T19:14:30.615502Z [info     ] request.completed              audio_seconds=1890.89 diarize=True dropped=0 duration_ms=97318.39 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=e8e350b6-a4f9-4660-b2cb-ddaa019a781b rtf=0.051 segments=120 service_name=monsum-speech size_bytes=60508526 status_code=200 trace_id=e8e350b6-a4f9-4660-b2cb-ddaa019a781b vad=True vad_backend=silero words=4832
2026-11-01T19:14:30.615694Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:14:32.401877Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=125 request_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 service_name=monsum-speech trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6
2026-11-01T19:14:32.834193Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 service_name=monsum-speech trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6
2026-11-01T19:14:32.834369Z [info     ] Processing audio with duration 01:00:39.210 endpoint=/v1/audio/transcriptions request_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 service_name=monsum-speech trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6
2026-11-01T19:14:37.738900Z [info     ] VAD filter removed 11:44.760 of audio endpoint=/v1/audio/transcriptions request_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 service_name=monsum-speech trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6
2026-11-01T19:16:01.402353Z [info     ] transcription_completed        audio_seconds=3639.21 elapsed_ms=88568 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=226 num_words=8496 request_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 service_name=monsum-speech trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6
2026-11-01T19:17:35.277975Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=20 num_segments=1329 request_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 service_name=monsum-speech trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6
2026-11-01T19:17:36.421807Z [info     ] request.completed              audio_seconds=3639.21 diarize=True dropped=0 duration_ms=185721.04 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=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 rtf=0.05 segments=226 service_name=monsum-speech size_bytes=116454766 status_code=200 trace_id=0fe06b7b-a7f2-4e0d-845e-87b105878fe6 vad=True vad_backend=silero words=8496
2026-11-01T19:17:36.422025Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:17:38.522695Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=288 request_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 service_name=monsum-speech trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05
2026-11-01T19:17:38.930602Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 service_name=monsum-speech trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05
2026-11-01T19:17:38.930762Z [info     ] Processing audio with duration 01:30:49.010 endpoint=/v1/audio/transcriptions request_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 service_name=monsum-speech trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05
2026-11-01T19:17:45.951074Z [info     ] VAD filter removed 12:34.600 of audio endpoint=/v1/audio/transcriptions request_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 service_name=monsum-speech trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05
2026-11-01T19:19:56.832747Z [info     ] transcription_completed        audio_seconds=5449.01 elapsed_ms=137902 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=352 num_words=14391 request_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 service_name=monsum-speech trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05
2026-11-01T19:22:19.672113Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=10 num_segments=3148 request_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 service_name=monsum-speech trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05
2026-11-01T19:22:23.676140Z [info     ] request.completed              audio_seconds=5449.01 diarize=True dropped=0 duration_ms=287047.18 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=5846eab8-52d2-4788-92aa-7e0d8cab6e05 rtf=0.052 segments=352 service_name=monsum-speech size_bytes=174368366 status_code=200 trace_id=5846eab8-52d2-4788-92aa-7e0d8cab6e05 vad=True vad_backend=silero words=14391
2026-11-01T19:22:23.676344Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:22:25.669240Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=0 request_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 service_name=monsum-speech trace_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986
2026-11-01T19:22:25.669410Z [info     ] Processing audio with duration 01:33:50.680 endpoint=/v1/audio/transcriptions request_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 service_name=monsum-speech trace_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986
2026-11-01T19:22:32.714994Z [info     ] VAD filter removed 43:25.992 of audio endpoint=/v1/audio/transcriptions request_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 service_name=monsum-speech trace_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986
2026-11-01T19:23:57.444327Z [info     ] transcription_completed        audio_seconds=5630.68 elapsed_ms=91775 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=228 num_words=8152 request_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 service_name=monsum-speech trace_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986
2026-11-01T19:26:21.148472Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=12 num_segments=1379 request_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 service_name=monsum-speech trace_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986
2026-11-01T19:26:22.293665Z [info     ] request.completed              audio_seconds=5630.68 diarize=True dropped=0 duration_ms=238180.22 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=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 rtf=0.042 segments=228 service_name=monsum-speech size_bytes=180181806 status_code=200 trace_id=e1e8d622-1dc5-4a6e-871f-2c8e1982a986 vad=True vad_backend=silero words=8152
2026-11-01T19:26:22.293859Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:26:23.771983Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=244 request_id=caff80df-cdc8-4825-a168-d55d10ab8df6 service_name=monsum-speech trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6
2026-11-01T19:26:24.205460Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=caff80df-cdc8-4825-a168-d55d10ab8df6 service_name=monsum-speech trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6
2026-11-01T19:26:24.205791Z [info     ] Processing audio with duration 57:25.920 endpoint=/v1/audio/transcriptions request_id=caff80df-cdc8-4825-a168-d55d10ab8df6 service_name=monsum-speech trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6
2026-11-01T19:26:28.245677Z [info     ] VAD filter removed 03:45.432 of audio endpoint=/v1/audio/transcriptions request_id=caff80df-cdc8-4825-a168-d55d10ab8df6 service_name=monsum-speech trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6
2026-11-01T19:28:01.247001Z [info     ] transcription_completed        audio_seconds=3445.92 elapsed_ms=97041 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=250 num_words=9410 request_id=caff80df-cdc8-4825-a168-d55d10ab8df6 service_name=monsum-speech trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6
2026-11-01T19:29:29.322376Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=8 num_segments=1472 request_id=caff80df-cdc8-4825-a168-d55d10ab8df6 service_name=monsum-speech trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6
2026-11-01T19:29:30.676277Z [info     ] request.completed              audio_seconds=3445.92 diarize=True dropped=0 duration_ms=188176.7 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=caff80df-cdc8-4825-a168-d55d10ab8df6 rtf=0.054 segments=250 service_name=monsum-speech size_bytes=110269486 status_code=200 trace_id=caff80df-cdc8-4825-a168-d55d10ab8df6 vad=True vad_backend=silero words=9410
2026-11-01T19:29:30.676478Z [info     ] 127.0.0.1:59406 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-01T19:29:30.976805Z [info     ] Shutting down                  service_name=monsum-speech
2026-11-01T19:29:31.077665Z [info     ] Waiting for application shutdown. service_name=monsum-speech
2026-11-01T19:29:31.078177Z [info     ] Application shutdown complete. service_name=monsum-speech
2026-11-01T19:29:31.078487Z [info     ] Finished server process [2935188] service_name=monsum-speech