{
  "format": "parakeet-tdt-coreai-v1",
  "repository": "FluidVoice-Labs/fluid-speech-pro",
  "revision": "46027a3bffc5817ce8f9b29add0a062610134a90",
  "frame_buckets": [
    384
  ],
  "precision": "w8a16",
  "blank_id": 8192,
  "vocabulary_size": 8193,
  "durations": [
    0,
    1,
    2,
    3,
    4
  ],
  "maximum_symbols_per_frame": 10,
  "query_tile": 0,
  "relative_attention": "fourier",
  "fused_subsampling": false,
  "encoder_batch_size": 1,
  "encoder_batch_layout": "height",
  "wide_spatial_projections": false,
  "fused_qkv": false,
  "split_glu": false,
  "native_layer_norm": false,
  "bounded_norm_variance": false,
  "accurate_silu": true,
  "subsampling_valid_mask": true,
  "frame_cleaner": {
    "width": 1024,
    "hidden_size": 1024,
    "kernel_size": 15,
    "padded_mel_frames": 1
  },
  "transcription_style": "clean",
  "encoder_stage_boundaries": [
    0,
    4,
    8,
    12,
    16,
    20,
    24
  ],
  "convolution_mask": "before_bias_free_glu",
  "depthwise_convolution": "explicit_nine_taps",
  "decoder_graph_layout": "batched-only",
  "parameter_count": 629125766,
  "frame_cleaner_parameter_count": 2117632,
  "languages": [
    "en",
    "bg",
    "hr",
    "cs",
    "da",
    "nl",
    "et",
    "fi",
    "fr",
    "de",
    "el",
    "hu",
    "it",
    "lv",
    "lt",
    "mt",
    "pl",
    "pt",
    "ro",
    "sk",
    "sl",
    "es",
    "sv",
    "ru",
    "uk"
  ],
  "decoder_defaults": {
    "strategy": "greedy_tdt",
    "do_sample": false,
    "provenance": "https://huggingface.co/FluidVoice-Labs/fluid-speech-pro/blob/46027a3bffc5817ce8f9b29add0a062610134a90/README.md"
  }
}