d3ro-voice/memory
Yun Chan e2d17601a4 feat(meeting): ground AI transcript correction in learned vocabulary
AI polishing of a recorded or pasted transcript was a generic rewrite: it
cleaned fillers but left names and in-house terms mangled even when the app
already knew them. Polishing now corrects dictionary pronunciations and
typed identifiers deterministically before and after the model, and hands
the model the learned term list plus the user's own expressions with
explicit rules: rewrite a misheard name, product or in-house term to the
learned spelling, and never swap an ordinary noun or ending on similarity
alone. Dictation output is re-checked the same way after the model runs.
2026-11-06 17:22:54 +09:00
..
handoff-archive chore: 세션 핸드오프 — V2-7 완료 2026-04-13 01:28:55 +09:00
big-bang-prompt.md chore: 빅뱅 사이클 wrap-up — 핸드오프 + 상세 다음 세션 프롬프트 2026-04-11 09:45:20 +09:00
handoff-latest.md docs: 1.16.1 배포 결과 기록 2026-11-04 07:15:37 +09:00
handoff_rn_cli.md chore: 세션 핸드오프 — RN CLI 전환 빌드 정보 + 다음 작업 목록 2026-04-13 21:15:33 +09:00
project_status.md feat(meeting): ground AI transcript correction in learned vocabulary 2026-11-06 17:22:54 +09:00