{
  "architectures": [
    "ASTForAudioClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "dtype": "float32",
  "frequency_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 192,
  "id2label": {
    "0": "angry",
    "1": "disgusted",
    "2": "fearful",
    "3": "happy",
    "4": "neutral",
    "5": "sad",
    "6": "surprised"
  },
  "initializer_range": 0.02,
  "intermediate_size": 768,
  "label2id": {
    "angry": 0,
    "disgusted": 1,
    "fearful": 2,
    "happy": 3,
    "neutral": 4,
    "sad": 5,
    "surprised": 6
  },
  "layer_norm_eps": 1e-12,
  "max_length": 1024,
  "model_type": "audio-spectrogram-transformer",
  "num_attention_heads": 3,
  "num_hidden_layers": 12,
  "num_mel_bins": 128,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "time_stride": 16,
  "transformers_version": "5.0.0",
  "use_cache": false
}