{
  "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": "water",
    "1": "resident",
    "2": "transient",
    "3": "humpback",
    "4": "vessel",
    "5": "jingle",
    "6": "human"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "human": 6,
    "humpback": 3,
    "jingle": 5,
    "resident": 1,
    "transient": 2,
    "vessel": 4,
    "water": 0
  },
  "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"
}