search

m-bain / whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
BSD 2-Clause "Simplified" License
11.33k stars 1.19k forks source link

Hugginface Diarization Authentication Issue #751

Open vishjain opened 5 months ago

vishjain commented 5 months ago

Keep getting this error whether I try diarization 3.0 or some other version despite accepting the user aggrements on HF - are there any fixes here:

torchaudio.set_audio_backend("soundfile") Could not download 'pyannote/speaker-diarization' pipeline. It might be because the pipeline is private or gated so make sure to authenticate. Visit https://hf.co/settings/tokens to create your access token and retry with:

Pipeline.from_pretrained('pyannote/speaker-diarization', ... use_auth_token=YOUR_AUTH_TOKEN) If this still does not work, it might be because the pipeline is gated:

nkilm commented 3 months ago

pyannote.audio models are gated on hg.co, you have to fill a form before you download the models. After this, you should be able to download the pyannote models.