codingninja/w2v2-bert-pa-v0.2-num
04
1{2 "_name_or_path": "kdcyberdude/w2v2-bert-pa-v0.2",3 "activation_dropout": 0.0,4 "adapter_act": "relu",5 "adapter_kernel_size": 3,6 "adapter_stride": 2,7 "add_adapter": true,8 "apply_spec_augment": true,9 "architectures": [10 "Wav2Vec2BertForCTC"11 ],12 "attention_dropout": 0.0,13 "bos_token_id": 1,14 "classifier_proj_size": 768,15 "codevector_dim": 768,16 "conformer_conv_dropout": 0.1,17 "contrastive_logits_temperature": 0.1,18 "conv_depthwise_kernel_size": 31,19 "ctc_loss_reduction": "mean",20 "ctc_zero_infinity": true,21 "diversity_loss_weight": 0.1,22 "eos_token_id": 2,23 "feat_proj_dropout": 0.0,24 "feat_quantizer_dropout": 0.0,25 "feature_projection_input_dim": 160,26 "final_dropout": 0.1,27 "hidden_act": "swish",28 "hidden_dropout": 0.0,29 "hidden_size": 1024,30 "initializer_range": 0.02,31 "intermediate_size": 4096,32 "layer_norm_eps": 1e-05,33 "layerdrop": 0.0,34 "left_max_position_embeddings": 64,35 "mask_feature_length": 10,36 "mask_feature_min_masks": 0,37 "mask_feature_prob": 0.0,38 "mask_time_length": 10,39 "mask_time_min_masks": 2,40 "mask_time_prob": 0.0,41 "max_source_positions": 5000,42 "model_type": "wav2vec2-bert",43 "num_adapter_layers": 1,44 "num_attention_heads": 16,45 "num_codevector_groups": 2,46 "num_codevectors_per_group": 320,47 "num_hidden_layers": 24,48 "num_negatives": 100,49 "output_hidden_size": 1024,50 "pad_token_id": 66,51 "position_embeddings_type": "relative_key",52 "proj_codevector_dim": 768,53 "right_max_position_embeddings": 8,54 "rotary_embedding_base": 10000,55 "tdnn_dilation": [56 1,57 2,58 3,59 1,60 161 ],62 "tdnn_dim": [63 512,64 512,65 512,66 512,67 150068 ],69 "tdnn_kernel": [70 5,71 3,72 3,73 1,74 175 ],76 "torch_dtype": "float16",77 "transformers_version": "4.43.3",78 "use_intermediate_ffn_before_adapter": true,79 "use_weighted_layer_sum": false,80 "vocab_size": 79,81 "xvector_output_dim": 51282}83 