feat(separation): add PixIT task, ToTaToNet model and SpeechSeparation pipeline

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

6.38k stars 784 forks source link

feat(separation): add PixIT task, ToTaToNet model and SpeechSeparation pipeline #1676

Closed joonaskalda closed 5 months ago

joonaskalda commented 8 months ago

The goal of this pull request is to add the new PixIT task, ToTaToNet model, and a pipeline to perform joint speaker diarization/speech separation inference.

hbredin commented 5 months ago

🎉 Merged! Huge!