Tina

cosyvoice 3 train

9

During the training process, many issues were discovered. Here, I would like to remind the author that there is a problem with cosyvoice3.yaml on github. We hope to replace it...

flow里面缺少参数encoder

1

https://github.com/FunAudioLLM/CosyVoice/blob/main/cosyvoice/flow/flow.py#L278 具体在这里，训练的时候需要使用CausalMaskedDiffWithDiT 但是在定义里缺少self.encoder 应该跟原来的一样，但是由于cosyvoice3可能有更改，所以不确定是否直接可以替换。 另外，cosyvoice3.yaml和模型中的不符，望注意