Files
luke_scribe/benchmarks
lukehemmin 7327145d7a feat: implement full-platform STT API (v2.3 consensus plan)
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.
2026-08-12 16:01:21 +09:00
..

benchmarks

v0.1 도메인 벤치마크 (KO+EN 혼용어) — turbo vs large-v3 하이브리드 게이트.

  • manifest.yaml.example: 클립/정답/entity annotation 스키마
  • references/: 클립별 정답 전사문 (개인정보 포함 원본은 커밋 금지)
  • decisions/: 모델 결정 아티팩트 (default-model-v1.json)
luke-scribe bench benchmarks/manifest.yaml --output benchmarks/report.json --decision benchmarks/decisions/default-model-v1.json