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 pipeline #39

Open
wants to merge 19 commits into
base: fluent-ui-migration
Choose a base branch
from

Conversation

RHeckerIntel
Copy link
Collaborator

@RHeckerIntel RHeckerIntel commented Nov 20, 2024

Implement Whisper Pipeline for new UI

  1. Transcribe videos on the go and show subtitles
  2. Show transcription of video
  3. Allow navigation by clicking on transcription part
  4. Allow download of transcription once entire video is transcribed.
  5. Transcription is searchable
  6. Added performance metrics
image

image

Enabled the c++ part and added the base UI.
Actual video and subtitles showing etc needs to be implemented
Gen AI allows you to output chunks when return_timestamps is true.
The chunks are closer to actual sentences and the timestamps are better.
I parse these chunks to get to combine them into better sentences.
No tests and implementation is a bit ugly. But it works.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant