{
  "schema": "transcribe-golden-manifest-v1",
  "family": "whisper",
  "variant": "whisper-tiny",
  "source_model": {
    "hf_repo": "openai/whisper-tiny",
    "hf_revision": "169d4a4341b33bc18d8881c4b69c2e104e1cc0af"
  },
  "reference": {
    "kind": "transformers",
    "source": "https://github.com/huggingface/transformers",
    "revision": "v5.6.1",
    "entrypoint": "scripts/dump_reference_whisper_transformers.py"
  },
  "expected_dtype": "float32",
  "dtype_source": "config",
  "frontend": {
    "sample_rate": 16000,
    "n_mels": 80,
    "hop_length": 160,
    "fft_size": 400,
    "win_length": 400,
    "window": "hann_periodic",
    "normalization": "global",
    "preemphasis": null,
    "dither": null
  },
  "tokenizer_summary": {
    "type": "bpe",
    "vocab_size": 50258,
    "special_tokens": {
      "bos": 50257,
      "eos": 50257,
      "pad": 50257,
      "decoder_start": 50258,
      "transcribe": 50359,
      "translate": 50358,
      "no_timestamps": 50363,
      "prev_sot": 50361
    }
  },
  "capabilities": {
    "languages": [
      "en",
      "zh",
      "de",
      "es",
      "ru",
      "ko",
      "fr",
      "ja",
      "pt",
      "tr",
      "pl",
      "ca",
      "nl",
      "ar",
      "sv",
      "it",
      "id",
      "hi",
      "fi",
      "vi",
      "he",
      "uk",
      "el",
      "ms",
      "cs",
      "ro",
      "da",
      "hu",
      "ta",
      "no",
      "th",
      "ur",
      "hr",
      "bg",
      "lt",
      "la",
      "mi",
      "ml",
      "cy",
      "sk",
      "te",
      "fa",
      "lv",
      "bn",
      "sr",
      "az",
      "sl",
      "kn",
      "et",
      "mk",
      "br",
      "eu",
      "is",
      "hy",
      "ne",
      "mn",
      "bs",
      "kk",
      "sq",
      "sw",
      "gl",
      "mr",
      "pa",
      "si",
      "km",
      "sn",
      "yo",
      "so",
      "af",
      "oc",
      "ka",
      "be",
      "tg",
      "sd",
      "gu",
      "am",
      "yi",
      "lo",
      "uz",
      "fo",
      "ht",
      "ps",
      "tk",
      "nn",
      "mt",
      "sa",
      "lb",
      "my",
      "bo",
      "tl",
      "mg",
      "as",
      "tt",
      "haw",
      "ln",
      "ha",
      "ba",
      "jw",
      "su"
    ],
    "language_detection": true,
    "translation": true,
    "translation_target_languages": ["en"],
    "timestamps": [
      "segment",
      "word"
    ],
    "streaming": false,
    "speaker_diarization": false
  },
  "tolerance_file": "tests/tolerances/whisper-tiny.json",
  "cases": [
    {
      "audio": "jfk",
      "language": "en"
    },
    {
      "audio": "german",
      "language": "de"
    }
  ]
}