{
  "_name_or_path": "MIT/ast-finetuned-speech-commands-v2",
  "architectures": [
    "ASTForAudioClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "frequency_stride": 10,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "zero",
    "1": "one",
    "10": "#unk#",
    "11": "#pub#",
    "2": "two",
    "3": "three",
    "4": "four",
    "5": "five",
    "6": "six",
    "7": "seven",
    "8": "eight",
    "9": "nine"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "#pub#": 11,
    "#unk#": 10,
    "eight": 8,
    "five": 5,
    "four": 4,
    "nine": 9,
    "one": 1,
    "seven": 7,
    "six": 6,
    "three": 3,
    "two": 2,
    "zero": 0
  },
  "layer_norm_eps": 1e-12,
  "max_length": 128,
  "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": "4.26.1"
}