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]