tapir

Files

T

mathiasandClaude Sonnet 5.5 e182a6b07d docs(research): can a local model adjudicate two ASR transcripts?

Eleven local models, 120 calls each, scored against the speaker's blind answers
on 30 disagreements, with pass criteria fixed before the run. gemma4-31b (97%)
and gemma4-26b (92%) pass; nothing else clears accuracy and order-consistency.
Records why 31b is slow (MLX gives the same speed; Low Power Mode is the
unproven suspect) and the caveats: 30 items, one recording, thinking models
under-budgeted. Aggregate numbers only; this repo is public.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-10-01 23:14:27 +02:00

asr-kb-whisper-vs-pianissimo-2026-10-01.md

docs(research): kb-whisper vs pianissimo on one real hour of Swedish speech

2026-10-01 19:45:56 +02:00

audio-length-ceiling-2026-10-01.md

docs(research): measure the audio length ceiling before designing chunking (#33 )

2026-10-01 16:33:34 +02:00

chat-context-over-long-transcripts-2026-10-01.md

docs(research): chat over a long transcript -- what the offered models really hold

2026-10-01 17:08:13 +02:00

local-model-adjudicator-sweep-2026-10-01.md

docs(research): can a local model adjudicate two ASR transcripts?