You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Once again thanks for the great work. I believe there are couple of additions that can help with movies and TV dramas (specially action movies):
adding pyannote as VAD option. Version 4 of Silero-VAD has serious shortcomings in handling silence, and short bursts. The side effect is that the subs tend to start seconds earlier than actual dialog.
adding UVR audio separation models like MDX23C or Kim-vocal-2. Either of these models outperform demucs in terms of keeping vocals intact.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
Once again thanks for the great work. I believe there are couple of additions that can help with movies and TV dramas (specially action movies):
adding pyannote as VAD option. Version 4 of Silero-VAD has serious shortcomings in handling silence, and short bursts. The side effect is that the subs tend to start seconds earlier than actual dialog.
adding UVR audio separation models like MDX23C or Kim-vocal-2. Either of these models outperform demucs in terms of keeping vocals intact.
Just a thought.
BestRegards
Beta Was this translation helpful? Give feedback.
All reactions