Repository navigation
runner: diagnose missing streaming wakeword measurements - #193
Draft
rohanbanerjeee wants to merge 1 commit into
Draft
rohanbanerjeee wants to merge 1 commit into
rohanbanerjeee wants to merge 1 commit into
Conversation
|
MLCommons CLA bot: |
Author
|
recheck |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When the streaming runner receives an empty interface response or fewer than two complete processing pulses, it can fail with an
IndexErroror a NumPy zero-size reduction error. This change gives those failures measurement-specific diagnostics and points to the I2S,PROCESSING, andWW_DETECTEDsignal paths.It also explains the reference firmware's initial detection synchronization pulse and adds hardware-free regression tests for response parsing, incomplete pulse captures, valid timing and detection results, and the actual streaming script step with simulated board responses. Valid measurement calculations and detection scoring are unchanged.
Related to #175. This is a runner diagnostics contribution; it does not reproduce or resolve the reported DMA callback failure. The original hardware issue still requires a board-based reproduction.
Validation:
python -m unittest discover -s benchmark/runner/tests -v: all 17 tests pass with Python 3.9 and NumPy 1.26.4. Against the original runner code, the same suite produced 6 errors and 2 failures.git diff --check: passes.