config.json

{
  "_name_or_path": "facebook/wav2vec2-base",
  "activation_dropout": 0.0,
  "adapter_attn_dim": null,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForSpeechClassification"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 256,
  "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": "sum",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.1,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.0,
  "finetuning_task": "audio-classification",
  "freeze_feat_extract_train": true,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "VIVOSSPK01",
    "1": "VIVOSSPK02",
    "10": "VIVOSSPK11",
    "11": "VIVOSSPK12",
    "12": "VIVOSSPK13",
    "13": "VIVOSSPK14",
    "14": "VIVOSSPK15",
    "15": "VIVOSSPK16",
    "16": "VIVOSSPK17",
    "17": "VIVOSSPK18",
    "18": "VIVOSSPK19",
    "19": "VIVOSSPK20",
    "2": "VIVOSSPK03",
    "20": "VIVOSSPK21",
    "21": "VIVOSSPK22",
    "22": "VIVOSSPK23",
    "23": "VIVOSSPK24",
    "24": "VIVOSSPK25",
    "25": "VIVOSSPK26",
    "26": "VIVOSSPK27",
    "27": "VIVOSSPK28",
    "28": "VIVOSSPK29",
    "29": "VIVOSSPK30",
    "3": "VIVOSSPK04",
    "30": "VIVOSSPK31",
    "31": "VIVOSSPK32",
    "32": "VIVOSSPK33",
    "33": "VIVOSSPK34",
    "34": "VIVOSSPK35",
    "35": "VIVOSSPK36",
    "36": "VIVOSSPK37",
    "37": "VIVOSSPK38",
    "38": "VIVOSSPK39",
    "39": "VIVOSSPK40",
    "4": "VIVOSSPK05",
    "40": "VIVOSSPK41",
    "41": "VIVOSSPK42",
    "42": "VIVOSSPK43",
    "43": "VIVOSSPK44",
    "44": "VIVOSSPK45",
    "45": "VIVOSSPK46",
    "5": "VIVOSSPK06",
    "6": "VIVOSSPK07",
    "7": "VIVOSSPK08",
    "8": "VIVOSSPK09",
    "9": "VIVOSSPK10"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "VIVOSSPK01": "0",
    "VIVOSSPK02": "1",
    "VIVOSSPK03": "2",
    "VIVOSSPK04": "3",
    "VIVOSSPK05": "4",
    "VIVOSSPK06": "5",
    "VIVOSSPK07": "6",
    "VIVOSSPK08": "7",
    "VIVOSSPK09": "8",
    "VIVOSSPK10": "9",
    "VIVOSSPK11": "10",
    "VIVOSSPK12": "11",
    "VIVOSSPK13": "12",
    "VIVOSSPK14": "13",
    "VIVOSSPK15": "14",
    "VIVOSSPK16": "15",
    "VIVOSSPK17": "16",
    "VIVOSSPK18": "17",
    "VIVOSSPK19": "18",
    "VIVOSSPK20": "19",
    "VIVOSSPK21": "20",
    "VIVOSSPK22": "21",
    "VIVOSSPK23": "22",
    "VIVOSSPK24": "23",
    "VIVOSSPK25": "24",
    "VIVOSSPK26": "25",
    "VIVOSSPK27": "26",
    "VIVOSSPK28": "27",
    "VIVOSSPK29": "28",
    "VIVOSSPK30": "29",
    "VIVOSSPK31": "30",
    "VIVOSSPK32": "31",
    "VIVOSSPK33": "32",
    "VIVOSSPK34": "33",
    "VIVOSSPK35": "34",
    "VIVOSSPK36": "35",
    "VIVOSSPK37": "36",
    "VIVOSSPK38": "37",
    "VIVOSSPK39": "38",
    "VIVOSSPK40": "39",
    "VIVOSSPK41": "40",
    "VIVOSSPK42": "41",
    "VIVOSSPK43": "42",
    "VIVOSSPK44": "43",
    "VIVOSSPK45": "44",
    "VIVOSSPK46": "45"
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.0,
  "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": 0.05,
  "mask_time_selection": "static",
  "model_type": "wav2vec2",
  "no_mask_channel_overlap": false,
  "no_mask_time_overlap": false,
  "num_adapter_layers": 3,
  "num_attention_heads": 12,
  "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": 12,
  "num_negatives": 100,
  "output_hidden_size": 768,
  "pad_token_id": 0,
  "pooling_mode": "mean",
  "problem_type": "single_label_classification",
  "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": "4.42.3",
  "use_weighted_layer_sum": false,
  "vocab_size": 32,
  "xvector_output_dim": 512
}