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

whisper: Inference progress callback #1

Open
pminev opened this issue Aug 28, 2024 · 0 comments
Open

whisper: Inference progress callback #1

pminev opened this issue Aug 28, 2024 · 0 comments
Labels
enhancement New feature or request

Comments

@pminev
Copy link
Collaborator

pminev commented Aug 28, 2024

Implement the inference progress callback for whisper.cpp integration used here in the library.

The callback works as notifier how much of the audio is being processed (encoded and decoded).

Progress is calculated by measuring the seeking in the audio.

  1. Start at the beginning with variable seek 0
  2. Call progress callback to the client with seek
  3. Choose the best decoder - get it's seek_delta
  4. Add seek_delta to seek
  5. Back to 2) if the audio hasn't completed
@pminev pminev changed the title Support of whisper params whisper: Progress callback Aug 28, 2024
@iboB iboB added the enhancement New feature or request label Aug 29, 2024
@pminev pminev changed the title whisper: Progress callback whisper: Inference progress callback Aug 29, 2024
@iboB iboB transferred this issue from alpaca-core/ac-local Nov 18, 2024
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
Status: Todo
Development

No branches or pull requests

2 participants