I'm very interested in this space. Forgive my ignorance, but what makes this fit for Chinese voices, while unfit for English voices?
> This repository is forked from Real-Time-Voice-Cloning which only support English.
The base project spoke English because it had been trained on English text paired with English recordings. This speaks Mandarin because it has been trained on paired Mandarin text and recordings.
Amusingly, if you take one trained on English text/recording pairs and feed it French text, it will speak French with an English accent.