{
  "_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": "barswa",
    "1": "blakit1",
    "10": "greegr",
    "11": "hoopoe",
    "12": "litegr",
    "13": "ratcis1",
    "14": "rbsrob1",
    "15": "rerswa1",
    "16": "somgre1",
    "17": "thrnig1",
    "18": "wlwwar",
    "19": "woosan",
    "2": "cohmar1",
    "3": "colsun2",
    "4": "combul2",
    "5": "combuz1",
    "6": "comsan",
    "7": "eaywag1",
    "8": "eubeat1",
    "9": "gnbcam2"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "barswa": "0",
    "blakit1": "1",
    "cohmar1": "2",
    "colsun2": "3",
    "combul2": "4",
    "combuz1": "5",
    "comsan": "6",
    "eaywag1": "7",
    "eubeat1": "8",
    "gnbcam2": "9",
    "greegr": "10",
    "hoopoe": "11",
    "litegr": "12",
    "ratcis1": "13",
    "rbsrob1": "14",
    "rerswa1": "15",
    "somgre1": "16",
    "thrnig1": "17",
    "wlwwar": "18",
    "woosan": "19"
  },
  "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": "4.31.0.dev0"
}