config.json

{
  "activation_dropout": 0.1,
  "apply_spec_augment": true,
  "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_pos_batch_norm": false,
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "do_stable_layer_norm": false,
  "dtype": "float32",
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_dropout": 0.0,
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.1,
  "feat_proj_layer_norm": true,
  "final_dropout": 0.1,
  "finetuning_task": "audio-classification",
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "assamese",
    "1": "bengali",
    "2": "bodo",
    "3": "dogri",
    "4": "english",
    "5": "gujarati",
    "6": "hindi",
    "7": "kannada",
    "8": "kashmiri",
    "9": "konkani",
    "10": "maithili",
    "11": "malayalam",
    "12": "manipuri",
    "13": "marathi",
    "14": "nepali",
    "15": "odia",
    "16": "punjabi",
    "17": "sanskrit",
    "18": "santali",
    "19": "sindhi",
    "20": "tamil",
    "21": "telugu",
    "22": "urdu"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "assamese": 0,
    "bengali": 1,
    "bodo": 2,
    "dogri": 3,
    "english": 4,
    "gujarati": 5,
    "hindi": 6,
    "kannada": 7,
    "kashmiri": 8,
    "konkani": 9,
    "maithili": 10,
    "malayalam": 11,
    "manipuri": 12,
    "marathi": 13,
    "nepali": 14,
    "odia": 15,
    "punjabi": 16,
    "sanskrit": 17,
    "santali": 18,
    "sindhi": 19,
    "tamil": 20,
    "telugu": 21,
    "urdu": 22
  },
  "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": 12,
  "pad_token_id": 0,
  "problem_type": "single_label_classification",
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "transformers_version": "4.57.6",
  "use_weighted_layer_sum": false,
  "vocab_size": 32
}