RSDK-13440 Add support for tflite OWW models#18
Open
oliviamiller wants to merge 55 commits intoviam-modules:mainfrom
Open
RSDK-13440 Add support for tflite OWW models#18oliviamiller wants to merge 55 commits intoviam-modules:mainfrom
oliviamiller wants to merge 55 commits intoviam-modules:mainfrom
Conversation
…red-audio into openwakeword2
seanavery
reviewed
Mar 12, 2026
src/models/oww.py
Outdated
Collaborator
Author
There was a problem hiding this comment.
no we still need it to obtain the onnx models, but updated this block to also download the tflite files.
| scipy==1.17.0 | ||
| scikit-learn==1.8.0 | ||
| tqdm==4.67.3 | ||
| openwakeword==0.6.0 |
There was a problem hiding this comment.
[question] So tflite runtime is a dep of openwakeword?
hexbabe
reviewed
Mar 12, 2026
hexbabe
left a comment
There was a problem hiding this comment.
is it a breaking config change if the model type suffix is now required
Collaborator
Author
a suffix on the file path was was still required before it just had to be .onnx. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Benchmarks
Measured inference time on Raspberry Pi using 500 iterations of model.predict() on a single 80ms audio chunk (1280 samples, 16kHz mono int16):
onnx: mean 5.02ms, max 5.71ms
tflite: mean 4.07ms, max 4.71ms (~19% faster on ARM)
Testing
-Added unit tests
-manually tested onnx and tflite on mac and linux
Approvals
1 approval needed.