Batch+realtime transcription API: faster-whisper engine w/ EngineOwner (single GPU owner, OOM downgrade chain, persisted attempted_profiles), hardware-adaptive device manager (T0-T3 VRAM tiers), Redis/in-proc job queue w/ leases + crash recovery, postprocess (glossary/rules/LLM w/ egress guard), privacy-first result store (UUID keys, source deleted after transcribe), retention sweeper, API-key auth (HMAC digests, scopes, job ownership), WebSocket realtime lane (LocalAgreement), CLI (detect/transcribe/bench/serve/key), Docker, benchmark runner. 127 mock-based tests pass; ruff clean. Includes verification checklist and autoplan review notes.
samples
hello-ko-en.wav — 16kHz mono, 짧은 한국어+영문 기술용어 발화 샘플.
(라이선스 확인 후 실제 오디오 파일을 추가할 것. 개인정보 포함 원본 커밋 금지.)