marid/sst2
02
1{2 "_name_or_path": "facebook/wav2vec2-xls-r-300m",3 "activation_dropout": 0.0,4 "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": 0.0,12 "bos_token_id": 1,13 "classifier_proj_size": 256,14 "codevector_dim": 768,15 "contrastive_logits_temperature": 0.1,16 "conv_bias": true,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": "mean",45 "ctc_zero_infinity": false,46 "diversity_loss_weight": 0.1,47 "do_stable_layer_norm": true,48 "eos_token_id": 2,49 "feat_extract_activation": "gelu",50 "feat_extract_dropout": 0.0,51 "feat_extract_norm": "layer",52 "feat_proj_dropout": 0.0,53 "feat_quantizer_dropout": 0.0,54 "final_dropout": 0.0,55 "hidden_act": "gelu",56 "hidden_dropout": 0.0,57 "hidden_size": 1024,58 "initializer_range": 0.02,59 "intermediate_size": 4096,60 "layer_norm_eps": 1e-05,61 "layerdrop": 0.0,62 "mask_feature_length": 10,63 "mask_feature_min_masks": 0,64 "mask_feature_prob": 0.0,65 "mask_time_length": 10,66 "mask_time_min_masks": 2,67 "mask_time_prob": 0.05,68 "model_type": "wav2vec2",69 "num_adapter_layers": 3,70 "num_attention_heads": 16,71 "num_codevector_groups": 2,72 "num_codevectors_per_group": 320,73 "num_conv_pos_embedding_groups": 16,74 "num_conv_pos_embeddings": 128,75 "num_feat_extract_layers": 7,76 "num_hidden_layers": 24,77 "num_negatives": 100,78 "output_hidden_size": 1024,79 "pad_token_id": 43,80 "proj_codevector_dim": 768,81 "tdnn_dilation": [82 1,83 2,84 3,85 1,86 187 ],88 "tdnn_dim": [89 512,90 512,91 512,92 512,93 150094 ],95 "tdnn_kernel": [96 5,97 3,98 3,99 1,100 1101 ],102 "torch_dtype": "float32",103 "transformers_version": "4.16.2",104 "use_weighted_layer_sum": false,105 "vocab_size": 46,106 "xvector_output_dim": 512107}108 