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

zero-shot 在不同环境下同样的音频采样值不一样 #789

Open
superstring opened this issue Oct 17, 2024 · 1 comment
Open

zero-shot 在不同环境下同样的音频采样值不一样 #789

superstring opened this issue Oct 17, 2024 · 1 comment
Labels
algorithm Algorithm improvements & issues documentation Improvements or additions to documentation

Comments

@superstring
Copy link

通过下述代码进行采样:

spk_smp = chat.sample_audio_speaker(load_audio(audio_path, 24000))

采样的结果在本地没有问题,在基于pytorch/pytorch:2.1.0-cuda11.8-cudnn8-runtime 镜像的容器中会短一点,然后生成的音频有很明显的噪音

@fumiama fumiama added documentation Improvements or additions to documentation algorithm Algorithm improvements & issues labels Oct 17, 2024
@fumiama
Copy link
Member

fumiama commented Oct 17, 2024

因为该采样实质是经过DVAE做的编码,其输出结果与环境(CPU/GPU/显卡型号)有关。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
algorithm Algorithm improvements & issues documentation Improvements or additions to documentation
Projects
None yet
Development

No branches or pull requests

2 participants