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

如何解决paddlespeech_stream模式CPU占用极高问题? #75

Open
xiayezi2013 opened this issue Jan 26, 2024 · 2 comments
Open

如何解决paddlespeech_stream模式CPU占用极高问题? #75

xiayezi2013 opened this issue Jan 26, 2024 · 2 comments

Comments

@xiayezi2013
Copy link

在Linux机器上测试paddlespeech_stream模型时,CPU占用极高,基本上打满了:

./build/examples/paddlespeech_stream models/paddlespeech_stream/ models/paddlespeech_stream/long.wav

image
asr_cpu

我可以通过设置线程数OPENBLAS_NUM_THREADS解决cpu核数问题,但会造成性能低,且单核打满。

这种情况导致我无法在生产环境使用,请问有没有解决方案?

@chenkui164
Copy link
Owner

chenkui164 commented Jan 26, 2024

用这个项目吧,https://github.com/k2-fsa/sherpa-onnx
里面包含很多预训练模型,https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
如果太占CPU可以选择模型小一些的模型,或者使用int8量化的版本。

@yunqiushuiman
Copy link

conformer_online,这个流式的在测试长音频的时候, 运行到一半就卡住,或者报 Segmentation fault (core dumped)

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

No branches or pull requests

3 participants