{
  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
  "architectures": [
    "ASTForAudioClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "frequency_stride": 10,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "blues",
    "1": "classical",
    "2": "country",
    "3": "disco",
    "4": "hiphop",
    "5": "jazz",
    "6": "metal",
    "7": "pop",
    "8": "reggae",
    "9": "rock"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "blues": "0",
    "classical": "1",
    "country": "2",
    "disco": "3",
    "hiphop": "4",
    "jazz": "5",
    "metal": "6",
    "pop": "7",
    "reggae": "8",
    "rock": "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,
  "torch_dtype": "float32",
  "transformers_version": "4.37.2"
}