{ "_name_or_path": "facebook/w2v-bert-2.0", "activation_dropout": 0.0, "adapter_act": "relu", "adapter_attn_dim": null, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "apply_spec_augment": false, "architectures": [ "Wav2Vec2ForSequenceClassification" ], "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_bias": false, "conv_depthwise_kernel_size": 31, "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 ], "ctc_loss_reduction": "mean", "ctc_zero_infinity": false, "diversity_loss_weight": 0.1, "do_stable_layer_norm": false, "eos_token_id": 2, "feat_extract_activation": "gelu", "feat_extract_norm": "group", "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, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7", "8": "LABEL_8" }, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7, "LABEL_8": 8 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "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": 0.0, "max_source_positions": 5000, "model_type": "wav2vec2", "num_adapter_layers": 1, "num_attention_heads": 16, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 16, "num_conv_pos_embeddings": 128, "num_feat_extract_layers": 7, "num_hidden_layers": 24, "num_negatives": 100, "output_hidden_size": 1024, "pad_token_id": 35, "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": "4.40.1", "use_intermediate_ffn_before_adapter": false, "use_weighted_layer_sum": false, "vocab_size": 38, "xvector_output_dim": 512 }