Retrieval-based-Voice-Conversion-WebUI
Retrieval-based-Voice-Conversion-WebUI copied to clipboard
Suggestion: Migrate algorithm
I would like to know if it's possible to migrate the inference algorithm from web to realtime changer, as the algorithm in web appears to be be better.
They use the same algorithm but the real time voice changer splits audio stream into many segments so there may be some gliches.