doc: add tutorial evaluating the joint diarization/separation metrics

pyannote / pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

http://pyannote.github.io

MIT License

6.41k stars 789 forks source link

doc: add tutorial evaluating the joint diarization/separation metrics #1716

Closed clement-pages closed 2 months ago

clement-pages commented 6 months ago

This PR adds a new tutorial whose aim is to evaluate the pipeline seriously on speaker diarization, separation and ASR tasks.

What remains to be done before merging:

integrate #1676
Provide a checkpoint for the ToTatoNet model on HuggingFace

:warning: Audio files introduced by this PR are a bit large...

hbredin commented 6 months ago

FYI, @joonaskalda's PR has been merged.

clement-pages commented 5 months ago

⚠️ Audio files introduced by this PR are a bit large...

All the asset files needed by the tuto have been removed from the repo. Now, these files are retrieved from the web or their content has been hardcoded in the notebook.