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

FR: support faster-whisper #87

Closed
momobobe opened this issue Apr 22, 2023 · 3 comments · Fixed by #108
Closed

FR: support faster-whisper #87

momobobe opened this issue Apr 22, 2023 · 3 comments · Fixed by #108
Labels
enhancement New feature or request

Comments

@momobobe
Copy link

https:/guillaumekln/faster-whisper this is way faster than the original implementation. It's already done the job addressed by #22 (comment). Also #63 and #73 are somewhat useless solved with this one done @yihong0618 @zcf0508

@lewangdev
Copy link

I will take this issue.

Here is my faster-whisper colab for test: https:/lewangdev/faster-whisper-youtube

@lewangdev
Copy link

whisper 和 faster-whisper 接口和依赖不同,我的实现做了以下修改,感觉不适合发 PR 了

  • cpu 模式下,去掉了并发
  • cuda 模式下,需要安装 cuBLAS 11.x 和 cuDNN 8.x
  • 改写完之后目前 unit test 有一个失败

faster-whisper 的版本:

https:/lewangdev/autocut

@lewangdev
Copy link

#94

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

Successfully merging a pull request may close this issue.

3 participants