2026-11-02T12:26:09.806867Z [info     ] Started server process [4011921] service_name=monsum-speech
2026-11-02T12:26:09.806952Z [info     ] Waiting for application startup. service_name=monsum-speech
2026-11-02T12:26:09.807077Z [info     ] Application startup complete.  service_name=monsum-speech
2026-11-02T12:26:09.807724Z [info     ] Uvicorn running on http://127.0.0.1:8012 (Press CTRL+C to quit) service_name=monsum-speech
2026-11-02T12:26:14.522784Z [info     ] request.completed              duration_ms=0.8 endpoint=/health method=GET request_id=efcaad5e-dfe2-4398-8768-84aadaced016 service_name=monsum-speech status_code=200 trace_id=efcaad5e-dfe2-4398-8768-84aadaced016
2026-11-02T12:26:14.522898Z [info     ] 127.0.0.1:52402 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:26:14.540324Z [info     ] request.completed              duration_ms=0.7 endpoint=/health method=GET request_id=f663ff17-b228-4ea9-8e1c-89bf86f30c78 service_name=monsum-speech status_code=200 trace_id=f663ff17-b228-4ea9-8e1c-89bf86f30c78
2026-11-02T12:26:14.540784Z [info     ] 127.0.0.1:52410 - "GET /health HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:26:16.693635Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=152 request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:26:16.698738Z [info     ] lid_model_loading              endpoint=/v1/audio/transcriptions path=models/ambernet-langid/ambernet.onnx request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:26:17.225920Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:26:17.354916Z [info     ] whisper_model_loading          compute_type=float16 device=cuda endpoint=/v1/audio/transcriptions path=models/ct2-whisper-large-v3-turbo-mn-1 request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:26:17.863391Z [info     ] Processing audio with duration 46:25.250 endpoint=/v1/audio/transcriptions request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:26:20.988649Z [info     ] VAD filter removed 02:54.392 of audio endpoint=/v1/audio/transcriptions request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:27:41.557532Z [info     ] transcription_completed        audio_seconds=2785.25 elapsed_ms=84331 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=215 num_words=8220 request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
/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(
2026-11-02T12:27:42.971445Z [info     ] diarization_pipeline_loading   device=cuda endpoint=/v1/audio/transcriptions path=models/speaker-diarization-community-1 request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
/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)
2026-11-02T12:28:54.473418Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=2 num_segments=306 request_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 service_name=monsum-speech trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49
2026-11-02T12:28:54.720056Z [info     ] request.completed              audio_seconds=2785.25 diarize=True dropped=0 duration_ms=159934.68 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=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 rtf=0.057 segments=215 service_name=monsum-speech size_bytes=89128046 status_code=200 trace_id=c9b4d3a4-ac10-42ef-8451-ab7d03072f49 vad=True vad_backend=silero words=8220
2026-11-02T12:28:54.720321Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:28:56.494205Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=221 request_id=b25a6839-f66b-4af2-8c27-9bca47418f87 service_name=monsum-speech trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87
2026-11-02T12:28:56.928330Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=b25a6839-f66b-4af2-8c27-9bca47418f87 service_name=monsum-speech trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87
2026-11-02T12:28:56.928639Z [info     ] Processing audio with duration 01:00:09.620 endpoint=/v1/audio/transcriptions request_id=b25a6839-f66b-4af2-8c27-9bca47418f87 service_name=monsum-speech trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87
2026-11-02T12:29:01.315458Z [info     ] VAD filter removed 04:57.984 of audio endpoint=/v1/audio/transcriptions request_id=b25a6839-f66b-4af2-8c27-9bca47418f87 service_name=monsum-speech trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87
2026-11-02T12:30:36.054939Z [info     ] transcription_completed        audio_seconds=3609.62 elapsed_ms=99126 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=249 num_words=10213 request_id=b25a6839-f66b-4af2-8c27-9bca47418f87 service_name=monsum-speech trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87
2026-11-02T12:32:07.883443Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=3 num_segments=1428 request_id=b25a6839-f66b-4af2-8c27-9bca47418f87 service_name=monsum-speech trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87
2026-11-02T12:32:09.333057Z [info     ] request.completed              audio_seconds=3609.62 diarize=True dropped=0 duration_ms=194139.54 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=b25a6839-f66b-4af2-8c27-9bca47418f87 rtf=0.053 segments=249 service_name=monsum-speech size_bytes=115507886 status_code=200 trace_id=b25a6839-f66b-4af2-8c27-9bca47418f87 vad=True vad_backend=silero words=10213
2026-11-02T12:32:09.333240Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:32:10.906773Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=160 request_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e service_name=monsum-speech trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e
2026-11-02T12:32:11.337768Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=0.9999953508377075 request_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e service_name=monsum-speech trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e
2026-11-02T12:32:11.337933Z [info     ] Processing audio with duration 01:00:24.390 endpoint=/v1/audio/transcriptions request_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e service_name=monsum-speech trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e
2026-11-02T12:32:15.672894Z [info     ] VAD filter removed 23:55.096 of audio endpoint=/v1/audio/transcriptions request_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e service_name=monsum-speech trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e
2026-11-02T12:33:15.843163Z [info     ] transcription_completed        audio_seconds=3624.39 elapsed_ms=64505 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=169 num_words=5879 request_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e service_name=monsum-speech trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e
2026-11-02T12:34:48.888372Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=17 num_segments=886 request_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e service_name=monsum-speech trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e
2026-11-02T12:34:49.389777Z [info     ] request.completed              audio_seconds=3624.39 diarize=True dropped=0 duration_ms=159739.28 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=1278bd8b-5641-4f23-86ee-32ffd9d2480e rtf=0.044 segments=169 service_name=monsum-speech size_bytes=115980526 status_code=200 trace_id=1278bd8b-5641-4f23-86ee-32ffd9d2480e vad=True vad_backend=silero words=5879
2026-11-02T12:34:49.389943Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:34:50.543584Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=208 request_id=9875f1aa-577c-407c-a405-1eea0ba684bb service_name=monsum-speech trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb
2026-11-02T12:34:50.976444Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=9875f1aa-577c-407c-a405-1eea0ba684bb service_name=monsum-speech trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb
2026-11-02T12:34:50.976616Z [info     ] Processing audio with duration 31:30.890 endpoint=/v1/audio/transcriptions request_id=9875f1aa-577c-407c-a405-1eea0ba684bb service_name=monsum-speech trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb
2026-11-02T12:34:53.183096Z [info     ] VAD filter removed 04:36.568 of audio endpoint=/v1/audio/transcriptions request_id=9875f1aa-577c-407c-a405-1eea0ba684bb service_name=monsum-speech trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb
2026-11-02T12:35:37.899293Z [info     ] transcription_completed        audio_seconds=1890.89 elapsed_ms=46923 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=120 num_words=4832 request_id=9875f1aa-577c-407c-a405-1eea0ba684bb service_name=monsum-speech trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb
2026-11-02T12:36:25.942251Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=6 num_segments=957 request_id=9875f1aa-577c-407c-a405-1eea0ba684bb service_name=monsum-speech trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb
2026-11-02T12:36:26.387655Z [info     ] request.completed              audio_seconds=1890.89 diarize=True dropped=0 duration_ms=96871.37 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=9875f1aa-577c-407c-a405-1eea0ba684bb rtf=0.051 segments=120 service_name=monsum-speech size_bytes=60508526 status_code=200 trace_id=9875f1aa-577c-407c-a405-1eea0ba684bb vad=True vad_backend=silero words=4832
2026-11-02T12:36:26.387818Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:36:27.732014Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=125 request_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 service_name=monsum-speech trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6
2026-11-02T12:36:28.134815Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 service_name=monsum-speech trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6
2026-11-02T12:36:28.134961Z [info     ] Processing audio with duration 01:00:39.210 endpoint=/v1/audio/transcriptions request_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 service_name=monsum-speech trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6
2026-11-02T12:36:32.482821Z [info     ] VAD filter removed 11:44.760 of audio endpoint=/v1/audio/transcriptions request_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 service_name=monsum-speech trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6
2026-11-02T12:37:56.047217Z [info     ] transcription_completed        audio_seconds=3639.21 elapsed_ms=87912 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=226 num_words=8496 request_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 service_name=monsum-speech trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6
2026-11-02T12:39:29.552293Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=20 num_segments=1267 request_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 service_name=monsum-speech trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6
2026-11-02T12:39:30.673104Z [info     ] request.completed              audio_seconds=3639.21 diarize=True dropped=0 duration_ms=184203.33 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=c9845d45-6fe2-4549-8b3b-35463b2f97b6 rtf=0.05 segments=226 service_name=monsum-speech size_bytes=116454766 status_code=200 trace_id=c9845d45-6fe2-4549-8b3b-35463b2f97b6 vad=True vad_backend=silero words=8496
2026-11-02T12:39:30.673286Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:39:32.414103Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=288 request_id=5c6a1787-438b-499a-a50c-594665b65e7f service_name=monsum-speech trace_id=5c6a1787-438b-499a-a50c-594665b65e7f
2026-11-02T12:39:32.845337Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=5c6a1787-438b-499a-a50c-594665b65e7f service_name=monsum-speech trace_id=5c6a1787-438b-499a-a50c-594665b65e7f
2026-11-02T12:39:32.845501Z [info     ] Processing audio with duration 01:30:49.010 endpoint=/v1/audio/transcriptions request_id=5c6a1787-438b-499a-a50c-594665b65e7f service_name=monsum-speech trace_id=5c6a1787-438b-499a-a50c-594665b65e7f
2026-11-02T12:39:39.413685Z [info     ] VAD filter removed 12:34.600 of audio endpoint=/v1/audio/transcriptions request_id=5c6a1787-438b-499a-a50c-594665b65e7f service_name=monsum-speech trace_id=5c6a1787-438b-499a-a50c-594665b65e7f
2026-11-02T12:41:50.471718Z [info     ] transcription_completed        audio_seconds=5449.01 elapsed_ms=137626 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=352 num_words=14391 request_id=5c6a1787-438b-499a-a50c-594665b65e7f service_name=monsum-speech trace_id=5c6a1787-438b-499a-a50c-594665b65e7f
2026-11-02T12:44:11.761592Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=8 num_segments=2945 request_id=5c6a1787-438b-499a-a50c-594665b65e7f service_name=monsum-speech trace_id=5c6a1787-438b-499a-a50c-594665b65e7f
2026-11-02T12:44:15.646472Z [info     ] request.completed              audio_seconds=5449.01 diarize=True dropped=0 duration_ms=284779.12 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=5c6a1787-438b-499a-a50c-594665b65e7f rtf=0.051 segments=352 service_name=monsum-speech size_bytes=174368366 status_code=200 trace_id=5c6a1787-438b-499a-a50c-594665b65e7f vad=True vad_backend=silero words=14391
2026-11-02T12:44:15.646660Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:44:17.598200Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=0 request_id=3714535e-c030-4ba4-b0e7-55a6f9784945 service_name=monsum-speech trace_id=3714535e-c030-4ba4-b0e7-55a6f9784945
2026-11-02T12:44:17.598357Z [info     ] Processing audio with duration 01:33:50.680 endpoint=/v1/audio/transcriptions request_id=3714535e-c030-4ba4-b0e7-55a6f9784945 service_name=monsum-speech trace_id=3714535e-c030-4ba4-b0e7-55a6f9784945
2026-11-02T12:44:24.201322Z [info     ] VAD filter removed 43:25.992 of audio endpoint=/v1/audio/transcriptions request_id=3714535e-c030-4ba4-b0e7-55a6f9784945 service_name=monsum-speech trace_id=3714535e-c030-4ba4-b0e7-55a6f9784945
2026-11-02T12:45:48.826635Z [info     ] transcription_completed        audio_seconds=5630.68 elapsed_ms=91228 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=228 num_words=8152 request_id=3714535e-c030-4ba4-b0e7-55a6f9784945 service_name=monsum-speech trace_id=3714535e-c030-4ba4-b0e7-55a6f9784945
2026-11-02T12:48:12.165605Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=11 num_segments=1327 request_id=3714535e-c030-4ba4-b0e7-55a6f9784945 service_name=monsum-speech trace_id=3714535e-c030-4ba4-b0e7-55a6f9784945
2026-11-02T12:48:13.292975Z [info     ] request.completed              audio_seconds=5630.68 diarize=True dropped=0 duration_ms=237225.87 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=3714535e-c030-4ba4-b0e7-55a6f9784945 rtf=0.042 segments=228 service_name=monsum-speech size_bytes=180181806 status_code=200 trace_id=3714535e-c030-4ba4-b0e7-55a6f9784945 vad=True vad_backend=silero words=8152
2026-11-02T12:48:13.293160Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:48:14.684129Z [info     ] vad_completed                  backend=silero endpoint=/v1/audio/transcriptions num_segments=244 request_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 service_name=monsum-speech trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313
2026-11-02T12:48:15.116344Z [info     ] asr_language_detected          detected_language=mn diverted=False endpoint=/v1/audio/transcriptions probability=1.0 request_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 service_name=monsum-speech trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313
2026-11-02T12:48:15.116501Z [info     ] Processing audio with duration 57:25.920 endpoint=/v1/audio/transcriptions request_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 service_name=monsum-speech trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313
2026-11-02T12:48:19.018267Z [info     ] VAD filter removed 03:45.432 of audio endpoint=/v1/audio/transcriptions request_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 service_name=monsum-speech trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313
2026-11-02T12:49:52.015121Z [info     ] transcription_completed        audio_seconds=3445.92 elapsed_ms=96899 endpoint=/v1/audio/transcriptions model=models/ct2-whisper-large-v3-turbo-mn-1 num_dropped=0 num_segments=250 num_words=9410 request_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 service_name=monsum-speech trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313
2026-11-02T12:51:19.790764Z [info     ] diarization_completed          endpoint=/v1/audio/transcriptions num_embeddings=6 num_segments=1458 request_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 service_name=monsum-speech trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313
2026-11-02T12:51:21.116196Z [info     ] request.completed              audio_seconds=3445.92 diarize=True dropped=0 duration_ms=187660.0 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=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 rtf=0.054 segments=250 service_name=monsum-speech size_bytes=110269486 status_code=200 trace_id=0eb847fa-6b92-484d-a5fb-d2ca4d6a5313 vad=True vad_backend=silero words=9410
2026-11-02T12:51:21.116380Z [info     ] 127.0.0.1:52426 - "POST /v1/audio/transcriptions HTTP/1.1" 200 service_name=monsum-speech
2026-11-02T12:51:21.417055Z [info     ] Shutting down                  service_name=monsum-speech
2026-11-02T12:51:21.516935Z [info     ] Waiting for application shutdown. service_name=monsum-speech
2026-11-02T12:51:21.517410Z [info     ] Application shutdown complete. service_name=monsum-speech
2026-11-02T12:51:21.517642Z [info     ] Finished server process [4011921] service_name=monsum-speech