{
  "architectures": [
    "ASTForAudioClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "dtype": "float32",
  "frequency_stride": 10,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "cat",
    "1": "cow",
    "2": "crow",
    "3": "dog",
    "4": "frog",
    "5": "hen",
    "6": "insects",
    "7": "pig",
    "8": "rooster",
    "9": "sheep"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "cat": 0,
    "cow": 1,
    "crow": 2,
    "dog": 3,
    "frog": 4,
    "hen": 5,
    "insects": 6,
    "pig": 7,
    "rooster": 8,
    "sheep": 9
  },
  "layer_norm_eps": 1e-12,
  "max_length": 1024,
  "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,
  "transformers_version": "5.0.0"
}