Commit graph

2 commits

Author SHA1 Message Date
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
Yun Chan
648c7e4f4d refactor(meeting): share the transcript polish prompt with tests
Move the polish instructions into their own module so the prompt the app
sends, the unit tests and the local-model probe use the same text. Tests
now pin the two rules that matter: fix a misheard name or in-house term to
the learned spelling, and never swap an ordinary word on similarity alone.

Verified against the local model with the real learned corpus: 하람록에 was
rewritten to HaramLog에 and the dictionary pronunciation 디에로 to D3RO,
while a natural sentence with no learned term came back with no word
substitutions. Recorded the trap that this model returns empty content
unless thinking is disabled.
2026-11-06 21:47:16 +09:00