config.json

{
  "activation_dropout": 0.1,
  "adapter_attn_dim": null,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": false,
  "architectures": [
    "Wav2Vec2ForAudioFrameClassification"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 256,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": true,
  "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,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": true,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.0,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 1024,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7",
    "8": "LABEL_8",
    "9": "LABEL_9",
    "10": "LABEL_10",
    "11": "LABEL_11",
    "12": "LABEL_12",
    "13": "LABEL_13",
    "14": "LABEL_14",
    "15": "LABEL_15",
    "16": "LABEL_16",
    "17": "LABEL_17",
    "18": "LABEL_18",
    "19": "LABEL_19",
    "20": "LABEL_20",
    "21": "LABEL_21",
    "22": "LABEL_22",
    "23": "LABEL_23",
    "24": "LABEL_24",
    "25": "LABEL_25",
    "26": "LABEL_26",
    "27": "LABEL_27",
    "28": "LABEL_28",
    "29": "LABEL_29",
    "30": "LABEL_30"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_10": 10,
    "LABEL_11": 11,
    "LABEL_12": 12,
    "LABEL_13": 13,
    "LABEL_14": 14,
    "LABEL_15": 15,
    "LABEL_16": 16,
    "LABEL_17": 17,
    "LABEL_18": 18,
    "LABEL_19": 19,
    "LABEL_2": 2,
    "LABEL_20": 20,
    "LABEL_21": 21,
    "LABEL_22": 22,
    "LABEL_23": 23,
    "LABEL_24": 24,
    "LABEL_25": 25,
    "LABEL_26": 26,
    "LABEL_27": 27,
    "LABEL_28": 28,
    "LABEL_29": 29,
    "LABEL_3": 3,
    "LABEL_30": 30,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "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": 0.0,
  "model_type": "wav2vec2",
  "num_adapter_layers": 3,
  "num_attention_heads": 16,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 24,
  "num_negatives": 100,
  "output_hidden_size": 1024,
  "pad_token_id": 0,
  "proj_codevector_dim": 256,
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.31.0",
  "use_weighted_layer_sum": false,
  "vocab_size": 32,
  "xvector_output_dim": 512
}