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

实时语音转换参数 #135

Open
zhengzhezhe opened this issue Feb 26, 2025 · 4 comments
Open

实时语音转换参数 #135

zhengzhezhe opened this issue Feb 26, 2025 · 4 comments

Comments

@zhengzhezhe
Copy link

作者你好
想请教一下,下面实时语音转换的这些参数分别应该设置为多少最好呀,block_time这些,
"block_time": 0.3,
"crossfade_length": 0.04,
"extra_time_ce": 2.5,
"extra_time": 0.5,
"extra_time_right": 0.02,
"diffusion_steps": 10,
"inference_cfg_rate": 0.7,
"max_prompt_length": 3.0,
非常期待你的回复~

@Plachtaa
Copy link
Owner

we will add the descriptions in README soon, thanks for feedback :)

@Plachtaa
Copy link
Owner

Hi, please check the real-time-GUI section of README for parameter explanations, hope this clarifies, thx

@zhengzhezhe
Copy link
Author

Hi, please check the real-time-GUI section of README for parameter explanations, hope this clarifies, thx

非常感谢!!!
根据readme里的解释我尝试把实时转换的代码迁移到linux上,将source音频切成0.5s的片段逐次输入模拟实时转换,最后拼接起来,发现转换后的音频在前端出现了一段静音段,而且尾部也没有转完,这种情况请问是什么原因导致的,该怎么解决呀?

@Plachtaa
Copy link
Owner

Plachtaa commented Mar 7, 2025

Hi, please check the real-time-GUI section of README for parameter explanations, hope this clarifies, thx

非常感谢!!! 根据readme里的解释我尝试把实时转换的代码迁移到linux上,将source音频切成0.5s的片段逐次输入模拟实时转换,最后拼接起来,发现转换后的音频在前端出现了一段静音段,而且尾部也没有转完,这种情况请问是什么原因导致的,该怎么解决呀?

我不知道你的code是如何组织的,所以这个需要你自己慢慢debug(

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