Why is there a background noise that sounds like wind for MaskGCT?

open-mmlab / Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

https://openhlt.github.io/amphion/

MIT License

7.81k stars 590 forks source link

Why is there a background noise that sounds like wind for MaskGCT? #352

Open lucasjinreal opened 1 week ago

lucasjinreal commented 1 week ago

output.wav.webm

仔细听会有幽灵一般的....

mysxs commented 1 week ago

你好，请问一下你使用哪个框架跑的？

lucasjinreal commented 1 week ago

就是maskgct。

yuantuo666 commented 1 week ago

Hi, could you provide the prompt wav & text, and target text & length?

BTW, we prefer English issues, ref.

honghee99 commented 1 week ago

我合成语音也有这个问题，背景音有点大

lucasjinreal commented 6 days ago

@jiaqili3 ??

jiaqili3 commented 6 days ago

Hi @lucasjinreal, currently I don't think there's an answer to your issue of background noise and I don't think it's a software bug. Maybe try different sampling hyperparams to see if it gets better. Thanks

jiaqili3 commented 6 days ago

@lucasjinreal sorry for closing your issue mistakenly, I reopened it