Questions about Training, Models, and Plan for Chinese TTS

open-mmlab / Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

https://openhlt.github.io/amphion/

MIT License

4.28k stars 364 forks source link

Questions about Training, Models, and Plan for Chinese TTS #221

Closed LIUKAI0815 closed 2 weeks ago

LIUKAI0815 commented 3 weeks ago

Could the current TTS support Chinese datasets?

jiaqili3 commented 3 weeks ago

Hi, our TTS models currently support English datasets, Chinese dataset support is currently in development for valle. For valle it only needs changing g2p to Chinese g2p like pypinyin, phonemizer. Alhough the public release of such a Chinese model is still in future plan.

LIUKAI0815 commented 2 weeks ago

Thank you for your answer