{
  "activation_dropout": 0.1,
  "add_adapter": false,
  "architectures": [
    "Data2VecForAudioModel"
  ],
  "attention_dropout": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_pos_kernel_size": 19,
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.0,
  "final_dropout": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "mask_time_prob": 0.05,
  "max_position_embeddings": 512,
  "model_type": "data2vec",
  "num_attention_heads": 12,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 5,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "proj_codevector_dim": 256,
  "torch_dtype": "float32",
  "transformers_version": "4.17.0.dev0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 32
}