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

关于同一模型,用不同方式合成声音效果不同的问题 #20

Open
lijielijie opened this issue Jun 17, 2022 · 3 comments
Open

Comments

@lijielijie
Copy link

针对同一个训练好的模型,我使用了三种不同的声音合成方式:
1、在aistudio使用paddlespeech的python synthesize_e2e.py命令合成语音
2、在本地使用本项目的python synthesize_e2e.py命令合成语音
3、在本地使用python gui/main.py窗体合成语音

效果依次是:
完美
有微弱电流音
个别字发不出声音

所以想问一下,第3种的合成效果能不能改造一下,使其效果尽量跟第2种一样

@jerryuhoo
Copy link
Owner

检查一下你的phone_id.txt是否一致,main.py是写死的路径所以要检查一下路径是否正确

@lijielijie
Copy link
Author

还有个问题,每次训练不同人声的时候,在生成TextGrid对齐文件之前,也都要重新训练一次MFA的模型吗

@jerryuhoo
Copy link
Owner

如果你的新数据足够多,建议重新训练,如果之前训练MFA模型的数据比较多,也可以不用重新训练。

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