-
Notifications
You must be signed in to change notification settings - Fork 317
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
chore: Add Docker configuration for SenseVoice OpenAI server #26
base: main
Are you sure you want to change the base?
Conversation
前几天测试单次推理GPU利用率比较低,能不能支持单次同时推理多个音频文件呢? |
这个得让官方的人来改了,对项目内核的代码我不熟。我只是提供了一个接口兼容的代码,从示例的 webui.py 里改过来的。 |
有碰到过内存爆掉的情况吗,比如这个#28 (comment) |
我自己测试CPU推理的8分钟音频,内存用量维持在 2G,推理耗时大概20秒的样子。 |
请问,有更改过那些参数吗? 我试过用demo.py推理其他的几秒钟音频是正常的,几分钟的就爆。 |
没有改过,就用官方示例那个 webui.py 里的。 |
又试了下,CPU可以推理长语音,换成GPU还是会爆 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
rename docker as service/python/http
@AndersonBY 是不是还要增加一个上传音频文件的接口? |
这里直接是直接上传的了
|
可以在接口里的file支持传入bytes吗?这样如果有实时采集麦克风的场景也可以用上,这里看openai的api应该也是支持的: |
高并发场景下有测试过吗?我用funasr 跑的iic/SenseVoice 无法做到线程安全 |
似乎长音频会自动切换到CPU? 我处理了一个60分钟的音频,发现GPU负载0,CPU倒是蹦到44%了。 |
效果真的又快又好,打算日常使用,所以增加一个提供 OpenAI 兼容的推理服务接口。