{
  "_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": "overdrive",
    "1": "distortion",
    "10": "low reduct",
    "11": "high boost",
    "12": "high reduct",
    "2": "chorus",
    "3": "flanger",
    "4": "phaser",
    "5": "tremolo",
    "6": "reverb",
    "7": "feedback delay",
    "8": "slapback delay",
    "9": "low boost"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "chorus": "2",
    "distortion": "1",
    "feedback delay": "7",
    "flanger": "3",
    "high boost": "11",
    "high reduct": "12",
    "low boost": "9",
    "low reduct": "10",
    "overdrive": "0",
    "phaser": "4",
    "reverb": "6",
    "slapback delay": "8",
    "tremolo": "5"
  },
  "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,
  "qkv_bias": true,
  "time_stride": 10,
  "torch_dtype": "float32",
  "transformers_version": "4.30.2"
}