I’ve tried all models and the voice is very choppy. It feels like it’s trying to read out loud the sentences as they are generated, instead of buffering them before. Can this be improved in order for stack Chan to sound better and more stable?
Version 1.3.1
I’ve tried all models and the voice is very choppy. It feels like it’s trying to read out loud the sentences as they are generated, instead of buffering them before. Can this be improved in order for stack Chan to sound better and more stable?
Version 1.3.1