modelscope/FunCodec

Release of CN TTS model

lucasjinreal opened this issue · 6 comments

lucasjinreal commented

Looks like LauraTTS have Chinese demo, will consider opensource the pretrained model?

ZhihaoDU commented

Currently, the released LauraTTS model is trained on the LibriTTS corpus. I think it is not able to synthesize Chinese directly. The Chinese synthesis model is under internal development and test. We may release it in the future.

  • 👍2
lucasjinreal commented

@ZhihaoDU https://lauragpt.github.io/ where does these Chinese synthesis come from?

ZhihaoDU commented

@ZhihaoDU https://lauragpt.github.io/ where does these Chinese synthesis come from?

Chinese cases in this page are generated by LauraGPT rather than LauraTTS, despite they have a similar architecture but different training data. While current released LauraTTS model is trained on LibriTTS, LauraGPT is trained on Librispeech, LibriTTS, AiShell and Aishell-2 and etc.

lucasjinreal commented

Oh, then, I mean LauraGPT, English only model is useless for me.

  • 😄1
deyituo commented

@lucasjinreal laoge, you are 666.

lucasjinreal commented

@deyituo Big iron, don't know what u say.