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
There are so many options and nobody tells which works the best. I'm currently working with speech female voice, with some noice.
I did cleaned original audio with iZotope a bit, with assistant
I guess firstly I need to use crepe as it should give better pitch? svc pre-hubert -fm crepe
Then I should enable new model instead of legacy default one? svc pre-config -t so-vits-svc-4.0v1
What is quickvc? What does it give? svc pre-config -t quickvc
Also there were option -na which someone said works better on female voice
Then I supplied 30 minutes of audio and it's sounds okay but not the best after 100 epochs. And it changed barely after 243
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.
-
There are so many options and nobody tells which works the best. I'm currently working with speech female voice, with some noice.
I did cleaned original audio with iZotope a bit, with assistant
I guess firstly I need to use crepe as it should give better pitch?
svc pre-hubert -fm crepeThen I should enable new model instead of legacy default one?
svc pre-config -t so-vits-svc-4.0v1What is quickvc? What does it give?
svc pre-config -t quickvcAlso there were option
-nawhich someone said works better on female voiceThen I supplied 30 minutes of audio and it's sounds okay but not the best after 100 epochs. And it changed barely after 243
Beta Was this translation helpful? Give feedback.
All reactions