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
I'm trying to perform speaker diarizaion and match the results with whisper produced phrases.
As @Majdoddinsuggested - I tried to insert 5 sec. silence part to audio to make Whisper break the phrase on such delimeters, but it doesn't work: whisper sometimes put both parts of delimetered phrase in one text segment.
So my questions is: how phrase breaking works in general?
Doe's anybody has suggestions how to make Whisper break the phrase in needed place?
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
Uh oh!
There was an error while loading. Please reload this page.
-
I'm trying to perform speaker diarizaion and match the results with whisper produced phrases.
As @Majdoddin suggested - I tried to insert 5 sec. silence part to audio to make Whisper break the phrase on such delimeters, but it doesn't work: whisper sometimes put both parts of delimetered phrase in one text segment.
So my questions is: how phrase breaking works in general?
Doe's anybody has suggestions how to make Whisper break the phrase in needed place?
Beta Was this translation helpful? Give feedback.
All reactions