d3ro-voice/apps/desktop/src
Yun Chan 3aa68f466c fix(meeting): keep polish from inventing markers or dropping qualifiers
The local model follows the polish instructions only most of the time: in
repeated runs it added a [00:00] or [화자 1] marker that was never in the
audio, and it turned "사실 거의 근간" into "사실 근간". Both change what the
meeting record says, so they are now enforced in code instead of hoped for
in the prompt: markers absent from the original chunk are stripped, and
meaning qualifiers the speaker said are restored from that chunk.

The instructions themselves were re-measured on the model: a fixed removal
list, an explicit qualifier example and a marker ban keep the filler cleanup
without touching ordinary words, and the same wording is used by the app,
the tests and the probe. Unknown-word repair still depends on the model.
2026-11-06 23:24:30 +09:00
..
main fix(meeting): keep polish from inventing markers or dropping qualifiers 2026-11-06 23:24:30 +09:00
preload feat(meeting): correct transcripts with vocabulary learned from typing 2026-11-05 21:58:28 +09:00
renderer chore: land in-progress workspace changes before 1.16.2 2026-11-05 21:58:44 +09:00