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

微调sovits模型n_speaker的问题 #1787

Open
yc930401 opened this issue Nov 19, 2024 · 2 comments
Open

微调sovits模型n_speaker的问题 #1787

yc930401 opened this issue Nov 19, 2024 · 2 comments

Comments

@yc930401
Copy link

作者您好呀,我想尝试微调一个大概几千人音色的sovits模型。前面做了5人和50人音色实验,在大概100-200个epoch就能把训练集覆盖到的音色学得很像了。但是我目前我在训练800+人音色的sovits模型,到了700个epoch,训练集的音色都还没有学得很像。不清楚是epoch还要继续增加的原因,还是s2_train中有个参数n_speakers=300这个的原因。想请教一下,是不是底模用了300人的音色训练呢?如果我想用更多人的音色,是直接改s2_train.json中的n_speakers再微调就管用嘛?还是需要重新用vits代码 https://github.com/jaywalnut310/vits 训练一个底模呢?或者用别的什么代码嘛?

@XXXXRT666
Copy link
Contributor

要是我没记错的话,n_speakers没有任何用

@XXXXRT666
Copy link
Contributor

用vits的代码必定报错,用这个仓库的代码,wiki里有写怎么做

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

2 participants