- cross-posted to:
- opensource@lemmy.ml
Very cool tool. I tried out the medium-size model on a Russian video, and the English subtitles that it generated were much more accurate than YouTube's autotranslated captions.
Very cool tool. I tried out the medium-size model on a Russian video, and the English subtitles that it generated were much more accurate than YouTube's autotranslated captions.
Anyone know if it supports speaker diarization? Or maybe some fork of it does?
Based on the help text it doesn't seem to yet. There's a discussion thread on github requesting it though