krishnareddy/asr_example
07
1{2 "_name_or_path": "facebook/wav2vec2-base",3 "activation_dropout": 0.0,4 "adapter_attn_dim": null,5 "adapter_kernel_size": 3,6 "adapter_stride": 2,7 "add_adapter": false,8 "apply_spec_augment": true,9 "architectures": [10 "Wav2Vec2ForCTC"11 ],12 "attention_dropout": 0.1,13 "bos_token_id": 1,14 "classifier_proj_size": 256,15 "codevector_dim": 256,16 "contrastive_logits_temperature": 0.1,17 "conv_bias": false,18 "conv_dim": [19 512,20 512,21 512,22 512,23 512,24 512,25 51226 ],27 "conv_kernel": [28 10,29 3,30 3,31 3,32 3,33 2,34 235 ],36 "conv_stride": [37 5,38 2,39 2,40 2,41 2,42 2,43 244 ],45 "ctc_loss_reduction": "mean",46 "ctc_zero_infinity": false,47 "diversity_loss_weight": 0.1,48 "do_stable_layer_norm": false,49 "eos_token_id": 2,50 "feat_extract_activation": "gelu",51 "feat_extract_norm": "group",52 "feat_proj_dropout": 0.1,53 "feat_quantizer_dropout": 0.0,54 "final_dropout": 0.0,55 "freeze_feat_extract_train": true,56 "hidden_act": "gelu",57 "hidden_dropout": 0.1,58 "hidden_size": 768,59 "initializer_range": 0.02,60 "intermediate_size": 3072,61 "layer_norm_eps": 1e-05,62 "layerdrop": 0.0,63 "mask_channel_length": 10,64 "mask_channel_min_space": 1,65 "mask_channel_other": 0.0,66 "mask_channel_prob": 0.0,67 "mask_channel_selection": "static",68 "mask_feature_length": 10,69 "mask_feature_min_masks": 0,70 "mask_feature_prob": 0.0,71 "mask_time_length": 10,72 "mask_time_min_masks": 2,73 "mask_time_min_space": 1,74 "mask_time_other": 0.0,75 "mask_time_prob": 0.05,76 "mask_time_selection": "static",77 "model_type": "wav2vec2",78 "no_mask_channel_overlap": false,79 "no_mask_time_overlap": false,80 "num_adapter_layers": 3,81 "num_attention_heads": 12,82 "num_codevector_groups": 2,83 "num_codevectors_per_group": 320,84 "num_conv_pos_embedding_groups": 16,85 "num_conv_pos_embeddings": 128,86 "num_feat_extract_layers": 7,87 "num_hidden_layers": 12,88 "num_negatives": 100,89 "output_hidden_size": 768,90 "pad_token_id": 0,91 "proj_codevector_dim": 256,92 "tdnn_dilation": [93 1,94 2,95 3,96 1,97 198 ],99 "tdnn_dim": [100 512,101 512,102 512,103 512,104 1500105 ],106 "tdnn_kernel": [107 5,108 3,109 3,110 1,111 1112 ],113 "torch_dtype": "float32",114 "transformers_version": "4.36.2",115 "use_weighted_layer_sum": false,116 "vocab_size": 32,117 "xvector_output_dim": 512118}119 