feat(mobile): on-device speaker-turn segmentation#6
Merged
Conversation
Wire the shared SpeakerSegmenter (Sortformer/FluidAudio) into the iOS app. The mic buffer now fans out to both the Transcriber and the Segmenter; on a detected speaker-turn boundary the Transcriber is finalized so the utterance is split. This breaks apart multi-person ambient conversation that SpeechAnalyzer would otherwise merge into one line when speakers don't pause. Turn segmentation only — no speaker labels. Toggle in Settings (default on); models download once on first enable, and load failure degrades to plain transcription. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Wire the shared
SpeakerSegmenter(Sortformer/FluidAudio, fromCore/) into the iOS app.What
Transcriberand theSpeakerSegmenter.Transcriberis finalized (finalizeThroughLatest()), splitting the utterance at the speaker change.AppController, now available on iOS because the engine lives inStenoCore.Why
Without it, iOS has no
sourcesplit (everything ismic), so a multi-person in-person conversation with no pauses merges into one long line. Segmentation breaks it at speaker changes.Turn segmentation only — no speaker labels (no "who"). Toggle in Settings (default on); the Sortformer model downloads once on first enable, and load failure degrades to plain transcription.
Verification
Mobile simulator build succeeds. Runtime (mic → segmentation → split lines) is a device step.
🤖 Generated with Claude Code