{
  "architectures": [
    "ASTForAudioClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "frequency_stride": 10,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "_silence_",
    "1": "_unknown_",
    "10": "four",
    "11": "fox",
    "12": "green",
    "13": "horse",
    "14": "nine",
    "15": "one",
    "16": "red",
    "17": "seven",
    "18": "six",
    "19": "ten",
    "2": "black",
    "20": "three",
    "21": "two",
    "22": "white",
    "3": "blue",
    "4": "brown",
    "5": "cat",
    "6": "dog",
    "7": "eight",
    "8": "fish",
    "9": "five"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "_silence_": "0",
    "_unknown_": "1",
    "black": "2",
    "blue": "3",
    "brown": "4",
    "cat": "5",
    "dog": "6",
    "eight": "7",
    "fish": "8",
    "five": "9",
    "four": "10",
    "fox": "11",
    "green": "12",
    "horse": "13",
    "nine": "14",
    "one": "15",
    "red": "16",
    "seven": "17",
    "six": "18",
    "ten": "19",
    "three": "20",
    "two": "21",
    "white": "22"
  },
  "layer_norm_eps": 1e-12,
  "max_length": 128,
  "model_type": "audio-spectrogram-transformer",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "num_mel_bins": 128,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "time_stride": 10,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3"
}