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

服务器部署问题,求大佬帮忙 #2423

Open
lower01 opened this issue Mar 13, 2025 · 6 comments
Open

服务器部署问题,求大佬帮忙 #2423

lower01 opened this issue Mar 13, 2025 · 6 comments
Labels
question Further information is requested

Comments

@lower01
Copy link

lower01 commented Mar 13, 2025

Image

例如这个中文流式语音识别服务文档,如果我是想测试whisper-large-v3的ASR效果,我该如何设置参数,之前已经在modelscope社区下载了模型文件到本地了并传到服务器上了:

Image

请问我该如何设置这个服务端参数?

@lower01 lower01 added the question Further information is requested label Mar 13, 2025
@WThirteen
Copy link

理论上你把model_dir 这里 设置为你下载的whisper路径就可以了

@lower01
Copy link
Author

lower01 commented Mar 17, 2025

理论上你把model_dir 这里 设置为你下载的whisper路径就可以了

那估计没有这么简单,CPU版和GPU版教程我都试过很多次whisper-large-v3了,不管是自己预先下载的还是自动下载的,都无法启动服务,cpu版我试sensevoice-small和paraformer-large都可以,GPU版示例的paraformer-large可以,但是多次尝试sensevoice-small和whisper-large-v3都不行,也都是从modelscope中下载的,应该是项目中提供的处理脚本并没有支持whisper

@WThirteen
Copy link

理论上你把model_dir 这里 设置为你下载的whisper路径就可以了

那估计没有这么简单,CPU版和GPU版教程我都试过很多次whisper-large-v3了,不管是自己预先下载的还是自动下载的,都无法启动服务,cpu版我试sensevoice-small和paraformer-large都可以,GPU版示例的paraformer-large可以,但是多次尝试sensevoice-small和whisper-large-v3都不行,也都是从modelscope中下载的,应该是项目中提供的处理脚本并没有支持whisper

换了之后发现似乎是模型缺少某个参数是吗。我似乎遇到这样的问题。

@lansfair
Copy link

因为GPU版会自动导出torchscript,但whisper-large-v3并不支持这么做

@lower01
Copy link
Author

lower01 commented Mar 20, 2025 via email

@lansfair
Copy link

修改cpp里的代码逻辑,去掉导出torchscript的部分,重写加载模型的逻辑,再重新编译

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants