{
  "_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": "onboard",
    "1": "restock",
    "2": "return",
    "3": "unknown"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "onboard": "0",
    "restock": "1",
    "return": "2",
    "unknown": "3"
  },
  "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": "4.38.1"
}