search

abdeladim-s / subsai

🎞️ Subtitles generation tool (Web-UI + CLI + Python package) powered by OpenAI's Whisper and its variants 🎞️
https://abdeladim-s.github.io/subsai/
GNU General Public License v3.0
1.15k stars 96 forks source link

support voice separation #137

Open read8873 opened 3 weeks ago

read8873 commented 3 weeks ago

When there are both voice and music, whisper tends to output "music" instead of the text of voice. Consider support add voice separation