[Team B] Sherpa AI backend #82
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
Stauntop-code
approved these changes
Feb 26, 2025
|
Been struggling with offline diarization, so I Just tried pushing the actual models for the speech-to-text. That push got rejected due to file size, so I'm going to go ahead and just mark this as ready for review. If anyone wants to test the speech-to-text, you will have to manually download the following and extract them into the assets folder: |
FlyingWaffleDev
force-pushed
the
teamb-yappy-sherpa-ai-backend
branch
from
da78dbd to
4dd3d63
Compare
FlyingWaffleDev
force-pushed
the
teamb-yappy-sherpa-ai-backend
branch
from
4dd3d63 to
52b69aa
Compare
FlyingWaffleDev
force-pushed
the
teamb-yappy-sherpa-ai-backend
branch
from
205b600 to
24a6449
Compare
|
Progress:
Will hopefully have the kinks ironed out in the next few days. |
will implement more of the required ai stuff in later commits
FlyingWaffleDev
force-pushed
the
teamb-yappy-sherpa-ai-backend
branch
from
24a6449 to
feee6de
Compare
Z4sythe
approved these changes
Mar 5, 2025
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Outdated suggestions cannot be applied.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.
Initial pass at an AI speech-to-text backend for Yappy.
This is still missing speaker diarization (which I am working on). Will swap from draft to an actual pull request once I'm done.
Current code is missing the actual AI models, I'm still trying to optimize for size/efficacy.
If you want to test it yourself, though, you'll need to grab both a streaming and non-streaming ASR model from here.
Either grab the ones mentioned in the pubspec and drop them in assets as noted, or grab whichever you like and update the pubspec and the offline/online_model.dart files appropriately.
Once I get diarization working, you will also need a speaker recognition model and a speaker segmentation model.