lukehemmin
7327145d7a
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.
21 lines
484 B
Plaintext
21 lines
484 B
Plaintext
dataset_version: "1.0"
|
|
hotword_sets:
|
|
none: []
|
|
domain: [API, vLLM, FastAPI, Kubernetes, LLM, GPU]
|
|
clips:
|
|
- id: ko-en-001
|
|
audio_path: /secure/local/path/ko-en-001.wav
|
|
reference_path: references/ko-en-001.txt
|
|
language: ko
|
|
duration_sec: 30.0
|
|
entities:
|
|
- canonical: API
|
|
surface: API
|
|
start_char: 3
|
|
end_char: 6
|
|
- canonical: vLLM
|
|
surface: vLLM
|
|
start_char: 12
|
|
end_char: 16
|
|
tags: [clean, single-speaker]
|