{
  "schema": "transcribe-golden-manifest-v1",
  "family": "parakeet",
  "variant": "nemotron-3.5-asr-streaming-0.6b",
  "source_model": {
    "hf_repo": "nvidia/nemotron-3.5-asr-streaming-0.6b",
    "hf_revision": "24b151a851dd15909e1fc611b11bb2da52b9fc81"
  },
  "reference": {
    "kind": "nemo",
    "source": "https://github.com/NVIDIA-NeMo/NeMo",
    "revision": "6967f48fda2a",
    "entrypoint": "scripts/dump_reference_parakeet_nemo.py",
    "dump_args": ["--att-context-right", "13"]
  },
  "expected_dtype": "float32",
  "dtype_source": "manual",
  "frontend": {
    "sample_rate": 16000,
    "n_mels": 128,
    "hop_length": 160,
    "fft_size": 512,
    "win_length": 400,
    "window": "hann_periodic",
    "normalization": "none",
    "preemphasis": null,
    "dither": 1e-05
  },
  "tokenizer_summary": {
    "type": "sentencepiece",
    "vocab_size": 13087,
    "special_tokens": {
      "unk": 0,
      "blank": 13087
    },
    "has_language_tokens": true
  },
  "capabilities": {
    "languages": [
      "en-US", "en-GB", "es-US", "es-ES", "fr-FR", "fr-CA", "it-IT",
      "pt-BR", "pt-PT", "nl-NL", "de-DE", "tr-TR", "ru-RU", "ar-AR",
      "hi-IN", "ja-JP", "ko-KR", "vi-VN", "uk-UA", "pl-PL", "sv-SE",
      "cs-CZ", "nb-NO", "da-DK", "bg-BG", "fi-FI", "hr-HR", "sk-SK",
      "zh-CN", "hu-HU", "ro-RO", "et-EE", "el-GR", "lt-LT", "lv-LV",
      "mt-MT", "sl-SI", "he-IL", "th-TH", "nn-NO"
    ],
    "language_detection": true,
    "translation": false,
    "timestamps": [
      "token",
      "word"
    ],
    "streaming": true,
    "speaker_diarization": false
  },
  "tolerance_file": "tests/tolerances/nemotron-3.5-asr-streaming-0.6b.json",
  "cases": [
    {"audio": "jfk", "language": "en-US"}
  ]
}