skzheng

I think you haven't run 'prepro.py' first.

> The speaker has a very thick voice, but the cloned result sounds like a normal person. May be you could try split the voice into five seconds pieces, and...

> I tried using fatchord's WaveRNN model for the vocoder but I get a size mismatch error. do i need to modify something first before using a different pretrained model?...

Is it possible to implement the front end of a new language with MaryTTS?Then what should I do and what I need to prepare? Thanks?

@nvadigauvce ，Can you tell me which front-end do you use, and how to build a TTS system with Merlin for a new language( The language that Festival does not support.)....

@simonkingedinburgh It's very helpful, thanks very much.