yunchan/d3ro-voice
1
0
Fork 0
Code Issues Pull requests Projects Releases 3 Packages Wiki Activity Actions

feat(caption): stream live captions and polish finished lines in context

Browse source 
Replaces the fixed six-second batches with a streaming track per audio
source: the uncommitted audio is re-recognised every second and sent as a
partial with its agreed (stable) prefix, a short pause finalises the line,
and long unbroken speech is committed at Whisper segment boundaries. Idle
audio is trimmed so silence cannot produce invented sentences.

Finished lines are corrected by the local model against the previous lines
and replaced in place; edits that change too much are rejected. The
behaviour can be switched off in Settings.
This commit is contained in:
Yun Chan 2026-09-24 20:22:21 +09:00
parent db8d9448a3
commit 39b8e7448e
28 changed files with 827 additions and 217 deletions
Download patch file Download diff file Expand all files Collapse all files

4
packages/i18n/src/locales/en.json
View file

@ -1903,5 +1903,7 @@
"input.feedback.excludedFailed": "Exclusions could not be saved.",
"input.feedback.recommendationFailed": "Could not add {{app}} to exclusions.",
"popup.caption.waiting": "Listening… the first caption can take a few seconds",
"popup.caption.dragHint": "Drag to move · double-click to reset"
"popup.caption.dragHint": "Drag to move · double-click to reset",
"settings.captionRefine": "Polish captions with context",
"settings.captionRefine.desc": "The local AI fixes spacing, punctuation and misheard words in finished captions using the surrounding lines."
}