RVC-Boss

Because the pretrained self supervised feature model RVC used only supports 16k-320hop. (And nearly all hubert series SSL feature only supports 16k-320hop)

嗯，之前有人反馈了，后面抽空修一下。

no space no ( no ) You can rename first and try again.

A more powerful pretrained hubert model is needed.

It will automatically skip segments that are not suitable for training.

@gengzhichen Now it can use GPU.

You installed CPU version pytorch environment.

It is recommended that the sample size of different speakers should not differ too much. More epochs can make the trained model's inferred speech timbre more similar to the target...

https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/config.py#L129 You can try modifing self.gpu_mem

你这个英文系统之前系统装过python吗