VenetSpark

About Guided Attention loss

2

Hello . I try to use your model to finish melspec to melspec conversion task. I try to add a guided attention like this : dal_loss = (hp.lamda_attn_dal * dal_g...

I found that the identity loss seems like missing in the "train the G ", and in my opinion, the code is supposed to be : id_mc = self.G (...

I want to know the what number of g_loss_fake should be when training is over ? Thank you

尊敬的李老师和其他作者： 请问AGAIN适合于做cross-lingual VC吗？ 我使用了双语的语料“ESD”的数据集进行训练，发现中文为源，目标是英文语音时，效果并不好。请问您有何看法。

why I got random images?

1

It doesn't matter how many times I run this code, the result I get is a bunch of random images.

跪求linux命令行版

2

### Issues - [X] I have browsed through the Issues. 我已浏览过Issues，确定没有重复的建议。 ### Expected behavior 预期的功能 希望可以在linux使用把，谢谢 ### Approximate reference (optional) 近似的参考（可选） _No response_