Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Diff-svc, so-vits-svc效果对比 #58

Open
yygg678 opened this issue May 6, 2023 · 6 comments
Open

Diff-svc, so-vits-svc效果对比 #58

yygg678 opened this issue May 6, 2023 · 6 comments

Comments

@yygg678
Copy link

yygg678 commented May 6, 2023

  1. lora-svc 的效果有跟Diff-svc, so-vits-svc效果对比吗?我看他们用的soft-vc 特征, 多说话人svc 时音色有泄漏,whisper 的ppg 多人有这个问题吗?
  2. lora-svc 是否都支持转语音转换和唱歌转换,无论训练的speaker 数据是只有歌唱还是只有语音数据?
@MaxMax2016
Copy link
Collaborator

1,音色泄漏应该没有吧,可以用发布的模型进行测试,模型使用56个发音人训练
2,不支持语音转换,但是支持用语音数据训练歌声转换

@yygg678
Copy link
Author

yygg678 commented May 8, 2023

用发布的模型进行测试,singer0001 唱高音时破音了,音高pitch是1000多,针对这种情况,有什么好的方法吗?

@MaxMax2016
Copy link
Collaborator

https://github.com/PlayVoice/lora-svc/blob/main/svc_preprocess_f0.py#L13 模型训练的时候,设置了最高音为900,需要根据您的实际数据修改这个参数来训练模型

@KillauraHacks
Copy link

https://github.com/PlayVoice/lora-svc/blob/main/svc_preprocess_f0.py#L13 During model training, the highest pitch is set to 900. You need to modify this parameter according to your actual data to train the model

how do you find the highest pitch in your model and how do you find the number to use (eg. 900) that the pitch corresponds to in order to modify the parameter

@Liujingxiu23
Copy link

@yygg678 请问你实际对比操作了不,该方法和Diff-svc, so-vits-svc对比效果如何?

@yygg678
Copy link
Author

yygg678 commented Aug 12, 2023

@yygg678 请问你实际对比操作了不,该方法和Diff-svc, so-vits-svc对比效果如何?
看数据集吧,我数据集比较脏,so-vits-svc 好些,diff-svc 没有试试

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants