{
  "schema": "transcribe-golden-manifest-v1",
  "family": "sensevoice",
  "variant": "sensevoice-small",
  "source_model": {
    "hf_repo": "FunAudioLLM/SenseVoiceSmall",
    "hf_revision": "3eb3b4eeffc2f2dde6051b853983753db33e35c3"
  },
  "reference": {
    "kind": "author_repo_funasr",
    "source": "https://github.com/modelscope/FunASR",
    "revision": "v1.3.1",
    "entrypoint": "scripts/dump_reference_sensevoice_funasr.py"
  },
  "expected_dtype": "float32",
  "dtype_source": "manual",
  "frontend": {
    "sample_rate": 16000,
    "n_mels": 80,
    "hop_length": 160,
    "fft_size": 400,
    "win_length": 400,
    "window": "hamming",
    "normalization": "per_feature",
    "lfr_m": 7,
    "lfr_n": 6,
    "dither": 0.0
  },
  "tokenizer_summary": {
    "type": "sentencepiece",
    "vocab_size": 25055,
    "special_tokens": {
      "unk": 0,
      "bos": 1,
      "eos": 2,
      "lang_zh": 24884,
      "lang_en": 24885,
      "lang_yue": 24888,
      "lang_ja": 24892,
      "lang_ko": 24896,
      "lang_nospeech": 24992,
      "withitn": 25016,
      "woitn": 25017
    }
  },
  "capabilities": {
    "languages": ["zh", "yue", "en", "ja", "ko"],
    "language_detection": true,
    "translation": false,
    "timestamps": [],
    "streaming": false,
    "speaker_diarization": false
  },
  "tolerance_file": "tests/tolerances/sensevoice.json",
  "cases": ["jfk"]
}