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

Investigate on a better GPU usage #6

Closed
chainyo opened this issue Apr 2, 2023 · 3 comments · Fixed by #72
Closed

Investigate on a better GPU usage #6

chainyo opened this issue Apr 2, 2023 · 3 comments · Fixed by #72
Assignees
Labels
diarization Everything related to the diarization part enhancement New feature or request transcription Everything related to the transcription part

Comments

@chainyo
Copy link
Contributor

chainyo commented Apr 2, 2023

Check if it's possible to accelerate request batching on GPU with faster-whisper current implementation.

Some reads:

@chainyo chainyo added the enhancement New feature or request label Apr 2, 2023
@chainyo
Copy link
Contributor Author

chainyo commented Apr 7, 2023

This is a bit stale for the moment. But I will check how to implement it into faster-whisper lib soon.

@chainyo
Copy link
Contributor Author

chainyo commented May 10, 2023

I will see what's happening in this repo and see if I can improve our transcription code: https://github.com/m-bain/whisperX/blob/main/whisperx/asr.py

@chainyo chainyo added transcription Everything related to the transcription part diarization Everything related to the diarization part labels May 10, 2023
@aleksandr-smechov
Copy link
Contributor

Might be useful to consider: https://opennmt.net/CTranslate2/parallel.html?highlight=async

@chainyo chainyo linked a pull request Jun 1, 2023 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
diarization Everything related to the diarization part enhancement New feature or request transcription Everything related to the transcription part
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants