Xueyao Zhang

Hi @CuiLvYing, thanks for your efforts! Would you please attach some demos (such as the generated voices or your WebUI's video) like PR https://github.com/open-mmlab/Amphion/pull/56?

Hi @CuiLvYing, I'm confused about your samples. For VC, the converted audio will speak the source's content with the target's timbre. Please use your model to convert the samples of...

The naturalness, especically the intelligibility, is bad to me. So I recommend not to merge this PR unless there is a substantial improvement. @Adorable-Qin Please review the code and document...

Thanks for such a valuable question! Using Encodec as the latent feature is also our future "research" work. We appreciate that you use Amphion as your codebase! @Adorable-Qin Zihao, would...

Hi @Ching-Yee-Chan, if you have any further questions about EnCodec or feature alignment, feel free to re-open this issue!

Hi, have you downloaded the Opencpop dataset? If so, you need to replace the `[Opencpop dataset path]` with the real dataset path. The downloading instruction can be seen [here](https://github.com/open-mmlab/Amphion/blob/main/egs/datasets/README.md#opencpop).

Hi @ErLongHuDaoGe, if you have any further questions, feel free to re-open this issue!

Hi all, it looks like the bug has been fixed. If you have any further questions, feel free to re-open this issue, and we're glad to follow up!

Which model do you want to train? You've succeeded to install the environment. Next step is to choose a model and go ahead 😄 The supported tasks can be seen...

> And there are one very small mistake( thought it's unnecessary, I think you can fix it easily  @NoFish-528 Thanks for pointing that! @HeCheng0625 Please follow up with this