leubeem f097141e8a feat(atc): bias Whisper STT toward aviation phraseology ...

Replace the generic one-line Whisper prompt with a vocabulary-rich bias prompt
(phonetic alphabet, aviation number words, common phraseology, and the airline
telephony names pulled live from DEFAULT_AIRLINE_TELEPHONY) and set
temperature: 0. Aviation R/T is a constrained domain, so seeding the expected
vocabulary improves transcription of callsigns, runways, and readbacks — the
upstream input to the decision engine. Stays within the ~224-token prompt cap.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-15 14:47:22 +02:00

..

api

feat(atc): bias Whisper STT toward aviation phraseology

2026-06-15 14:47:22 +02:00

middleware

feat(server): per-user AI usage tracking, cost alerting, and endpoint hardening

2026-06-10 23:17:03 +02:00

models

feat(server): per-user AI usage tracking, cost alerting, and endpoint hardening

2026-06-10 23:17:03 +02:00

utils

feat(server): per-user AI usage tracking, cost alerting, and endpoint hardening

2026-06-10 23:17:03 +02:00