Replace Meeting AEC3 with LocalVQE v1.3; prepare v0.5.126 - #69
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Meeting cleanup now uses one embedded LocalVQE v1.3 model to reduce echo, background noise, and reverberation. It replaces AEC3 only in the Meeting microphone path; raw microphone and system tracks retain their original timeline. Live dictation and file/YouTube transcription are unchanged.
The standalone audio worker includes hash-pinned source/model inputs and a static CPU backend, adapts 256-sample inference hops to existing 10-ms transport frames, and flushes accepted audio on Stop/Pause/EOF. Packaging notices, cache identities, installed smoke validation, and German labels follow the replacement. Version 0.5.126 prepares the requested installer release.
Validation: 94 audio-worker tests, pinned upstream inference parity, release clippy, focused Python/packaging gates, version/cache invalidation regressions, and Ruff checks. GitHub runs the complete quality suite. x64 enhancement requires AVX2/FMA/F16C; the model checks support before inference. Short reference timing does not establish physical Teams/Zoom/Meet quality or long-duration performance.