config.json

{
  "activation_dropout": 0.0,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": false,
  "architectures": [
    "Wav2Vec2BERTForPreTraining"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "classifier_proj_size": 768,
  "codevector_dim": 768,
  "conformer_conv_dropout": 0.1,
  "contrastive_logits_temperature": 0.1,
  "conv_depthwise_kernel_size": 31,
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "eos_token_id": 2,
  "feat_proj_dropout": 0.0,
  "feat_quantizer_dropout": 0.0,
  "feature_projection_input_dim": 160,
  "final_dropout": 0.1,
  "hidden_act": "swish",
  "hidden_dropout": 0.0,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "left_max_position_embeddings": 64,
  "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,
  "max_source_positions": 5000,
  "model_type": "wav2vec2-bert",
  "num_adapter_layers": 1,
  "num_attention_heads": 16,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_hidden_layers": 24,
  "num_negatives": 100,
  "output_hidden_size": 1024,
  "pad_token_id": 0,
  "position_embeddings_type": "relative_key",
  "proj_codevector_dim": 768,
  "right_max_position_embeddings": 8,
  "rotary_embedding_base": 10000,
  "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": "4.37.0.dev0",
  "use_intermediate_ffn_before_adapter": false,
  "use_weighted_layer_sum": false,
  "vocab_size": null,
  "xvector_output_dim": 512
}