Isma/v2_50k
07
1{2 "_name_or_path": "../src/output_dirs/mixup_v2/checkpoint-50000",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 "Wav2Vec2Model"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": "none",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_norm": "group",51 "feat_proj_dropout": 0.0,52 "feat_quantizer_dropout": 0.0,53 "final_dropout": 0.1,54 "hidden_act": "gelu",55 "hidden_dropout": 0.1,56 "hidden_size": 768,57 "initializer_range": 0.02,58 "intermediate_size": 3072,59 "layer_norm_eps": 1e-05,60 "layerdrop": 0.1,61 "mask_feature_length": 10,62 "mask_feature_min_masks": 0,63 "mask_feature_prob": 0.0,64 "mask_time_length": 10,65 "mask_time_min_masks": 2,66 "mask_time_prob": 0.05,67 "model_type": "wav2vec2",68 "num_adapter_layers": 3,69 "num_attention_heads": 12,70 "num_codevector_groups": 2,71 "num_codevectors_per_group": 320,72 "num_conv_pos_embedding_groups": 16,73 "num_conv_pos_embeddings": 128,74 "num_feat_extract_layers": 7,75 "num_hidden_layers": 12,76 "num_negatives": 100,77 "output_hidden_size": 768,78 "pad_token_id": 0,79 "proj_codevector_dim": 256,80 "tdnn_dilation": [81 1,82 2,83 3,84 1,85 186 ],87 "tdnn_dim": [88 512,89 512,90 512,91 512,92 150093 ],94 "tdnn_kernel": [95 5,96 3,97 3,98 1,99 1100 ],101 "torch_dtype": "float32",102 "transformers_version": "4.25.1",103 "use_weighted_layer_sum": false,104 "vocab_size": 32,105 "xvector_output_dim": 512106}107 