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

Add support for OpenAI Whisper #687

Merged
merged 3 commits into from
Jun 6, 2023

Conversation

joshuaboniface
Copy link
Contributor

@joshuaboniface joshuaboniface commented Jun 4, 2023

Adds basic support for OpenAI Whisper (local) as an STT provider.

This is supported by the upstream SpeechRecognition library, so this is just the standard translation to/from Kalliope.

Several options have been implemented and documented, including the ability to "unformat" the resulting strings if desired.

Also caps the Ansible version below 5 to fix test failures.

@joshuaboniface joshuaboniface changed the base branch from master to dev June 4, 2023 15:24
@joshuaboniface joshuaboniface mentioned this pull request Jun 5, 2023
@joshuaboniface joshuaboniface marked this pull request as draft June 5, 2023 14:31
@Sispheor
Copy link
Member

Sispheor commented Jun 6, 2023

Tests are failling. I think we should block the max version of Ansible to 5 here and here

@joshuaboniface
Copy link
Contributor Author

I did notice that about the tests but I wasn't too sure how to handle that: anything you want me to do in this PR?

@joshuaboniface joshuaboniface marked this pull request as ready for review June 6, 2023 17:41
@Sispheor
Copy link
Member

Sispheor commented Jun 6, 2023

Yes you can try the proposed changes.

@joshuaboniface
Copy link
Contributor Author

Done, waiting on tests. I also accidentally added a commit for a second feature (FasterWhisper) which I force-pushed away, but that requires an upstream change to speech_recognition (Uberi/speech_recognition#693) before it can be added.

@joshuaboniface
Copy link
Contributor Author

And looks like that solved it, I suppose we can just keep that commit in here, I've updated the description.

@Sispheor Sispheor merged commit 5edc64b into kalliope-project:dev Jun 6, 2023
1 check passed
@Sispheor
Copy link
Member

Sispheor commented Jun 6, 2023

Thx. You can rebase your other PR so I can merge it

@joshuaboniface joshuaboniface deleted the whisper branch June 6, 2023 20:24
@jaggzh
Copy link

jaggzh commented Aug 15, 2023

Is this keeping the whisper model loaded [or is it loaded each call]? Mine seems slow even with tiny being used.

@jaggzh
Copy link

jaggzh commented Aug 15, 2023

Oh, this is great, btw! Thanks. :))

@joshuaboniface
Copy link
Contributor Author

@jaggzh I believe that SpeechRecognition is loading it each time, which is indeed very slow. I ended up abandoning this myself, and using a custom integration with my own https://github.com/joshuaboniface/remote-faster-whisper tool.

@jaggzh
Copy link

jaggzh commented Nov 6, 2023 via email

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.

None yet

3 participants