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.

Sign up for GitHub

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

Jump to bottom

[ENHANCEMENT] Adding batched inference support for transcription #76

Open
Jiltseb opened this issue Mar 12, 2024 · 2 comments
Open

[ENHANCEMENT] Adding batched inference support for transcription #76

Jiltseb opened this issue Mar 12, 2024 · 2 comments
Assignees
@Jiltseb
Labels
enhancement New feature or request

Comments

@Jiltseb
Copy link
Contributor

Jiltseb commented Mar 12, 2024 •
edited
Loading

Enhancement Description

  • Provides support for batched inference for high-speed transcription.
@Jiltseb Jiltseb added the enhancement New feature or request label Mar 12, 2024
@appoose
Copy link
Contributor

appoose commented Sep 23, 2024

PR for faster whisper is merged, but bugs exists ( @Jiltseb can you add more details down )

Suggestion 1: Keep our version in pypi ( aana-whisper ) and then use pyproject to install it.
Rationale: Faster-whisiper is not moving fast as we expected, and also project velocity is low, so there is less of a blocker in waiting for compatibility with future version. And the speed up is significant for us to warrant our own project to bring the benefits to our users.

@Jiltseb Jiltseb changed the title [ENHANCEMENT] Adding batch support for transcription [ENHANCEMENT] Adding batch support for transcription (multiple audios) Oct 29, 2024
@Jiltseb Jiltseb changed the title [ENHANCEMENT] Adding batch support for transcription (multiple audios) [ENHANCEMENT] Adding batched inference support for transcription Oct 29, 2024
@Jiltseb Jiltseb self-assigned this Oct 29, 2024
@Jiltseb
Copy link
Contributor Author

Jiltseb commented Oct 29, 2024 •
edited
Loading

PR opened for this ticket: #197
Current approach:

  1. Uses mobius-faster-whisper on Pypi.
  2. Faster whisper repo is getting updated but the Pypi release is not yet planned. Hence we would like to proceed with option 1 at the moment.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Jiltseb Jiltseb

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@appoose @Jiltseb