Puyuan Peng

Thanks! > 1. Did you train Encodec as well? To my knowledge the parameters are released too. But looking into your code, it seams that you trained it too. Now...

Thanks for your interests! Model parameters will be released by the end of this month.

Thanks! Neither the model or the codebase are based off of XTTS. We are discussing the licensing issue right now, might change the license in the future

Thanks! There are two possible way to have interjections: 1. If the prompt has sounds like that, it's possible that the model will add that to the generation spontaneously 2....

> > Thanks! There are two possible way to have interjections: > > > > 1. If the prompt has sounds like that, it's possible that the model will add...

It currently only support English, but our on-going work will make it support more languages

Thanks! I'll update the repo to give more detailed guidance on how to train and finetune the model on different datasets