unable to locate SRT file

MahmoudAshraf97 / whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

BSD 2-Clause "Simplified" License

3.28k stars 272 forks source link

unable to locate SRT file #59

Closed FeistyViking closed 1 year ago

FeistyViking commented 1 year ago

I run diarize.py and all seems to work fine and I can see all the outputs in temp_outputs but I am unable to locate the SRT file.

just running diarize should create the SRT file yes? or do I need to run whisper specifically first?

albusshin commented 1 year ago

+1, the last message I see from the terminal is

[NeMo W 2023-06-28 17:30:41 nemo_logging:349] /home/albusshin/.pyenv/versions/3.10.12/lib/python3.10/site-packages/transformers/pipelines/token_classification.py:169: UserWarning: `grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="none"` instead.
      warnings.warn(

albusshin commented 1 year ago

Oh I found it, it's actually in the same directory as the input audio file.

FeistyViking commented 1 year ago

oh interesting. my input audio file was stored in a location where my account may not have had write permissions to. I will try moving it to a directory I fully own and see if that works