{ "activation_dropout": 0.1, "apply_spec_augment": true, "architectures": [ "Wav2Vec2Model" ], "attention_dropout": 0.1, "bos_token_id": 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 ], "do_stable_layer_norm": false, "eos_token_id": 2, "feat_extract_activation": "gelu", "feat_extract_norm": "group", "feat_extract_out_grad_mult": 0.1, "feat_proj_dropout": 0.1, "final_dropout": 0.1, "freeze_feat_extract_train": true, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "layerdrop": 0.1, "mask_channel_length": 10, "mask_channel_min_space": 1, "mask_channel_other": 0.0, "mask_channel_prob": 0.008, "mask_channel_selection": "static", "mask_time_length": 10, "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_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, "transformers_version": "4.4.0.dev0", "vocab_size": 32 }