feat: Add realtime audio transcription #2
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Owner
Author
|
Now just waiting on mudler/LocalAI#5392 |
|
I guess this is still quite new and work-in-progress, but all the vendor cruft makes the code base a lot less appealing to me as a small command-line tool. Is it just temporary for now? |
Owner
Author
|
It's possible that I can remove it again. Presently it simplifies using a forked version of the realtime API library, but it also simplifies creating a Nix package because I can remove the So once the changes to the realtime API are resolved, I think that would be a good time to revisit it. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Attempt to add real time audio transcription. Initially it uses a very niave method of just sending chunks to be transcribed, with the previous chunk being joined with the current one.
It sort of works, but words get repeated and there are lots of mistakes. Push to talk doesn't work because when cancelling it, key presses from the transcription get in the way of the key presses to stop it.