Speech Recognition/Whisper word level scores or confidence output

[wobbble]

Hey,
Big thanks for awesome project!

It possible to add score/confidence for word level output when using Speech Recognition/Whisper model?
Would appreciate any direction/comments or suggestion where to dig to add it.
Happy to submit PR if I will success in it.

Thanks!

[decoder-sh-david]

Seconded, I have also not been able to successfully get word-level timestamps while running on webgpu. Would love to have both!

[hlevring]

Looks like it has been supported for a while
https://github.com/huggingface/transformers.js/releases/tag/2.4.0

[xenova]

Indeed, Transformers.js v3 w/ word-level timestamps should work! @decoder-sh-david let me know if you run into any issues.