search

jianfch / stable-ts

Transcription, forced alignment, and audio indexing with OpenAI's Whisper
MIT License
1.47k stars 167 forks source link

What would be nice #182

Open curiousbee2020 opened 1 year ago

curiousbee2020 commented 1 year ago

Just a suggestion - it would be great if stable-ts did speaker diarization too so that we have accurate timestamps for multi-speaker audio.

Thanks!

mirix commented 12 months ago

https://github.com/mirix/approaches-to-diarisation