{
  "_name_or_path": "imrajeshkr/distilhubert-finetuned-speech_commands",
  "activation_dropout": 0.1,
  "apply_spec_augment": false,
  "architectures": [
    "HubertForSequenceClassification"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.0,
  "feat_proj_layer_norm": false,
  "final_dropout": 0.0,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "A",
    "1": "B",
    "10": "K",
    "11": "L",
    "12": "M",
    "13": "N",
    "14": "O",
    "15": "Other",
    "16": "P",
    "17": "Q",
    "18": "R",
    "19": "S",
    "2": "C",
    "20": "T",
    "21": "U",
    "22": "V",
    "23": "W",
    "24": "X",
    "25": "Y",
    "26": "Z",
    "3": "D",
    "4": "E",
    "5": "F",
    "6": "G",
    "7": "H",
    "8": "I",
    "9": "J"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "A": "0",
    "B": "1",
    "C": "2",
    "D": "3",
    "E": "4",
    "F": "5",
    "G": "6",
    "H": "7",
    "I": "8",
    "J": "9",
    "K": "10",
    "L": "11",
    "M": "12",
    "N": "13",
    "O": "14",
    "Other": "15",
    "P": "16",
    "Q": "17",
    "R": "18",
    "S": "19",
    "T": "20",
    "U": "21",
    "V": "22",
    "W": "23",
    "X": "24",
    "Y": "25",
    "Z": "26"
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.0,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.05,
  "model_type": "hubert",
  "num_attention_heads": 12,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 2,
  "pad_token_id": 0,
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "use_weighted_layer_sum": false,
  "vocab_size": 32
}