config.json

{
  "activation_dropout": 0.0,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "WavLMForCTC"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 768,
  "contrastive_logits_temperature": 0.1,
  "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": "mean",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": true,
  "dtype": "float32",
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_dropout": 0.0,
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.1,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.0,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "<PAD>",
    "1": "<UNK>",
    "2": "<BOS>",
    "3": "<EOS>",
    "4": "|",
    "5": "AA",
    "6": "AE",
    "7": "AH",
    "8": "AW",
    "9": "AY",
    "10": "B",
    "11": "CH",
    "12": "D",
    "13": "DH",
    "14": "DX",
    "15": "EH",
    "16": "ER",
    "17": "EY",
    "18": "F",
    "19": "G",
    "20": "HH",
    "21": "IH",
    "22": "IY",
    "23": "JH",
    "24": "K",
    "25": "L",
    "26": "M",
    "27": "N",
    "28": "NG",
    "29": "OW",
    "30": "OY",
    "31": "P",
    "32": "R",
    "33": "S",
    "34": "SH",
    "35": "T",
    "36": "TH",
    "37": "UH",
    "38": "UW",
    "39": "V",
    "40": "W",
    "41": "Y",
    "42": "Z",
    "43": "ZH"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "<BOS>": 2,
    "<EOS>": 3,
    "<PAD>": 0,
    "<UNK>": 1,
    "AA": 5,
    "AE": 6,
    "AH": 7,
    "AW": 8,
    "AY": 9,
    "B": 10,
    "CH": 11,
    "D": 12,
    "DH": 13,
    "DX": 14,
    "EH": 15,
    "ER": 16,
    "EY": 17,
    "F": 18,
    "G": 19,
    "HH": 20,
    "IH": 21,
    "IY": 22,
    "JH": 23,
    "K": 24,
    "L": 25,
    "M": 26,
    "N": 27,
    "NG": 28,
    "OW": 29,
    "OY": 30,
    "P": 31,
    "R": 32,
    "S": 33,
    "SH": 34,
    "T": 35,
    "TH": 36,
    "UH": 37,
    "UW": 38,
    "V": 39,
    "W": 40,
    "Y": 41,
    "Z": 42,
    "ZH": 43,
    "|": 4
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "mask_channel_length": 10,
  "mask_channel_min_space": 1,
  "mask_channel_other": 0.0,
  "mask_channel_prob": 0.0,
  "mask_channel_selection": "static",
  "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_min_space": 1,
  "mask_time_other": 0.0,
  "mask_time_prob": 0.075,
  "mask_time_selection": "static",
  "max_bucket_distance": 800,
  "model_type": "wavlm",
  "num_adapter_layers": 3,
  "num_attention_heads": 16,
  "num_buckets": 320,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_ctc_classes": 80,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 24,
  "num_negatives": 100,
  "output_hidden_size": 1024,
  "pad_token_id": 0,
  "proj_codevector_dim": 768,
  "replace_prob": 0.5,
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "transformers_version": "4.57.3",
  "use_weighted_layer_sum": false,
  "vocab_size": 46,
  "xvector_output_dim": 512
}