machinelearningzuu/automatic-speech-recognition

1{2  "_name_or_path": "facebook/wav2vec2-large-960h",3  "activation_dropout": 0.1,4  "adapter_kernel_size": 3,5  "adapter_stride": 2,6  "add_adapter": false,7  "apply_spec_augment": true,8  "architectures": [9    "Wav2Vec2ForCTC"10  ],11  "attention_dropout": 0.1,12  "bos_token_id": 1,13  "classifier_proj_size": 256,14  "codevector_dim": 256,15  "contrastive_logits_temperature": 0.1,16  "conv_bias": false,17  "conv_dim": [18    512,19    512,20    512,21    512,22    512,23    512,24    51225  ],26  "conv_kernel": [27    10,28    3,29    3,30    3,31    3,32    2,33    234  ],35  "conv_stride": [36    5,37    2,38    2,39    2,40    2,41    2,42    243  ],44  "ctc_loss_reduction": "sum",45  "ctc_zero_infinity": false,46  "diversity_loss_weight": 0.1,47  "do_stable_layer_norm": false,48  "eos_token_id": 2,49  "feat_extract_activation": "gelu",50  "feat_extract_dropout": 0.0,51  "feat_extract_norm": "group",52  "feat_proj_dropout": 0.0,53  "feat_quantizer_dropout": 0.0,54  "final_dropout": 0.1,55  "hidden_act": "gelu",56  "hidden_dropout": 0.1,57  "hidden_dropout_prob": 0.1,58  "hidden_size": 1024,59  "initializer_range": 0.02,60  "intermediate_size": 4096,61  "layer_norm_eps": 1e-05,62  "layerdrop": 0.1,63  "mask_feature_length": 10,64  "mask_feature_min_masks": 0,65  "mask_feature_prob": 0.0,66  "mask_time_length": 10,67  "mask_time_min_masks": 2,68  "mask_time_prob": 0.05,69  "model_type": "wav2vec2",70  "num_adapter_layers": 3,71  "num_attention_heads": 16,72  "num_codevector_groups": 2,73  "num_codevectors_per_group": 320,74  "num_conv_pos_embedding_groups": 16,75  "num_conv_pos_embeddings": 128,76  "num_feat_extract_layers": 7,77  "num_hidden_layers": 24,78  "num_negatives": 100,79  "output_hidden_size": 1024,80  "pad_token_id": 0,81  "proj_codevector_dim": 256,82  "tdnn_dilation": [83    1,84    2,85    3,86    1,87    188  ],89  "tdnn_dim": [90    512,91    512,92    512,93    512,94    150095  ],96  "tdnn_kernel": [97    5,98    3,99    3,100    1,101    1102  ],103  "torch_dtype": "float32",104  "transformers_version": "4.17.0",105  "use_weighted_layer_sum": false,106  "vocab_size": 32,107  "xvector_output_dim": 512108}109