{
  "activation_dropout": 0.1,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2Model"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "conv_bias": false,
  "conv_dim": [
    64,
    64
  ],
  "conv_kernel": [
    40,
    40
  ],
  "conv_stride": [
    30,
    30
  ],
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "do_stable_layer_norm": true,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.1,
  "final_dropout": 0.1,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 128,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "mask_feature_length": 10,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_prob": 0.05,
  "model_type": "wav2vec2",
  "num_attention_heads": 2,
  "num_conv_pos_embedding_groups": 4,
  "num_conv_pos_embeddings": 64,
  "num_feat_extract_layers": 2,
  "num_hidden_layers": 2,
  "pad_token_id": 0,
  "transformers_version": "4.6.0.dev0",
  "vocab_size": 12
}