feat(audio-lab): add wavekat-zh Smart Turn fine-tune as a second turn backend - #44
Merged
Merged
Conversation
… backend Bumps wavekat-turn to 0.0.8 and enables the wavekat-smart-turn feature so audio-lab can load the Mandarin fine-tune from wavekat/smart-turn-ONNX alongside upstream Pipecat Smart Turn v3. Backend list now exposes both "pipecat" and "wavekat-zh"; the frontend seeds one default config per known backend so the two models show up side-by-side without manual setup. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The .nvmrc lives in frontend/, but nvm use was running from tools/audio-lab/ before the cd, so it could not pick up the pinned Node version and the make targets failed with exit 127. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
…ckend Pipeline Mode previously started empty and required manual setup, which hid the new wavekat-zh comparison behind extra clicks. Auto-seeds one pipeline per turn backend (paired with silero-vad, or the first available VAD config) on first load and whenever the saved list is empty, so the upstream Pipecat vs WaveKat fine-tune comparison shows up in Pipeline Mode by default. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
wavekat-eason
pushed a commit
that referenced
this pull request
May 15, 2026
🤖 I have created a release *beep* *boop* --- ## [0.0.15](v0.0.14...v0.0.15) (2026-05-14) ### Features * **audio-lab:** add wavekat-zh Smart Turn fine-tune as a second turn backend ([#44](#44)) ([07f92c8](07f92c8)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
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.
Summary
wavekat-turnto0.0.8and enables thewavekat-smart-turnfeature so audio-lab can load the Mandarin fine-tune fromwavekat/smart-turn-ONNX.wavekat-zhturn backend next topipecat; both share the same ONNX contract, only the weights differ.WAVEKAT_TURN_MODEL_DIRoffline override.The
wavekat-zhONNX is fetched from HuggingFace on first selection and cached under\$HF_HOME/hub/.Test plan
🤖 Generated with Claude Code