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

Expand speech-to-text #187

Closed
3 tasks done
jonatanklosko opened this issue Mar 31, 2023 · 1 comment
Closed
3 tasks done

Expand speech-to-text #187

jonatanklosko opened this issue Mar 31, 2023 · 1 comment
Labels
kind:feature New feature or request

Comments

@jonatanklosko
Copy link
Member

jonatanklosko commented Mar 31, 2023 •
edited
Loading

  • option to chunk long inputs (the chunk_length_s in hf/t pipeline)
  • option to output timestamps
  • whisper-specific option for configuring language and task (also see Encapsulate generation options in a config struct #193 (comment))
    • it is worth considering if we can make these configurable at runtime. For example instead of using forced_token_ids, perhaps we could make the initial decoder ids include the special tokens
@jonatanklosko jonatanklosko mentioned this issue Mar 31, 2023
Closed
@jonatanklosko jonatanklosko added the kind:feature New feature or request label Mar 31, 2023
@jonatanklosko jonatanklosko mentioned this issue Apr 6, 2023
Merged
@josevalim josevalim mentioned this issue May 19, 2023
Closed
@jonatanklosko
Copy link
Member Author

Closed in #238.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
kind:feature New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jonatanklosko