mathias/tapir
1
0
Fork 0
Code Issues 35 Pull Requests Actions Packages Projects Releases Wiki Activity

feat: upload audio, get a private Swedish transcript, discuss it (#33, ADR-033) #39

Merged
mathias merged 299 commits from feat/33-audio-upload-transcript into main 2026-10-03 14:13:37 +00:00
Conversation 8 Commits 299 Files Changed 104
+7 -4
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 59f2893434 - Show all commits
DECISIONS.md
+7 -4
View File
@@ -1601,10 +1601,13 @@ Mode on iguana is the unproven suspect).
plain words what was done — "reconciled from two transcripts: N differences, K uncertain" — and
lists the uncertain spots. A reconciled transcript is never presented as simply "the" transcript.
7. **Configuration.** `TAPIR_TRANSCRIBE_SECOND_MODEL` (empty = off), `TAPIR_RECONCILE_MODEL`
(required when a second engine is set), `TAPIR_RECONCILE_CHECK_ORDER` (off). The default job
timeout rises from 30 to 60 minutes: ~4 min of kb-whisper and ~40 s of pianissimo per hour of audio,
plus the adjudication.
7. **Configuration.** `TAPIR_RECONCILE_BASE_MODEL` (empty = off; the engine whose text is the base,
e.g. `iguana/pianissimo` — `TAPIR_TRANSCRIBE_MODEL` stays the other engine, e.g. kb-whisper),
`TAPIR_RECONCILE_MODEL` (the adjudicator; required when a base engine is set),
`TAPIR_RECONCILE_CHECK_ORDER` (off). All three models must be local aliases (`koala/` or `iguana/`):
a cloud alias is a start-up error, and the base engine must differ from the other one. The default
job timeout rises from 30 to 60 minutes: ~4 min of kb-whisper and ~40 s of pianissimo per hour of
audio, plus the adjudication.
8. **Not decided here.** A cloud adjudicator (rejected: private content); tuning the prompt; making
`gemma4-31b` the default; a "reconciling" progress state (the page says "transcribing" for the whole