search

JigsawStack / insanely-fast-whisper-api

An API to transcribe audio with OpenAI's Whisper Large v3!
MIT License
165 stars 23 forks source link

Diarization does not work #4

Open olsn opened 5 months ago

olsn commented 5 months ago

First of all: thank you for the nice project! It works really well - except when, i try to activate diarization.

The docker-log then shows: torchvision is not available - cannot save figures

The response of the rest-call is:

{
  "detail": "'NoneType' object has no attribute 'eval'"
}

I have not yet tried to install torchvision, but maybe that's all that's neede?

yoeven commented 5 months ago

Yes torchvision is needed but it should be installed automatically if you're loading it from the dockerfile. Also you would need to provide a hugging face API key to load the diarization model. Check it out here