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

Voice cracked when stream_batch is low. 声音在stream_batch低的时候有很多噪音 #832

Open
faw21 opened this issue Dec 3, 2024 · 1 comment
Labels
documentation Improvements or additions to documentation

Comments

@faw21
Copy link

faw21 commented Dec 3, 2024

When setting stream=True with a low stream_batch (assume 1 or 2), even though it decreases latency to first audio chunk by a lot (~150ms on 4090), the audio is very noisy. I tried concatenate all generated audio chunks and play them together after stream finished, the noise still persisted. This is also true even when stream_batch is default (24), I can hear that the point between two concatenated audio chunks have a tiny distortion. Is this a fixable issue? thanks.

在流式输出时把stream_batch降到1或者2时可以减少很多latency,但是音质受到很大音响,播放音频时有很大的、持续的电流声,音调也比非流式输出时要低。另外,即使用default batch size 24,我仍然可以在音频与音频连接处听到一些杂音,请问这个问题是否可以解决?是什么原因引起的?谢谢。

ChatTTS version:0.2.1

@fumiama
Copy link
Member

fumiama commented Dec 3, 2024

这是流式输出的原理导致的,无法有效解决,目前已经将杂音影响降至最低,可参考#521

@fumiama fumiama added the documentation Improvements or additions to documentation label Dec 3, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation
Projects
None yet
Development

No branches or pull requests

2 participants