GENG/hubert_ls_4500
036
1{2 "_name_or_path": "facebook/hubert-base-ls960",3 "activation_dropout": 0.1,4 "apply_spec_augment": true,5 "architectures": [6 "HubertForCTC"7 ],8 "attention_dropout": 0.1,9 "bos_token_id": 1,10 "classifier_proj_size": 256,11 "conv_bias": false,12 "conv_dim": [13 512,14 512,15 512,16 512,17 512,18 512,19 51220 ],21 "conv_kernel": [22 10,23 3,24 3,25 3,26 3,27 2,28 229 ],30 "conv_stride": [31 5,32 2,33 2,34 2,35 2,36 2,37 238 ],39 "ctc_loss_reduction": "mean",40 "ctc_zero_infinity": false,41 "do_stable_layer_norm": false,42 "eos_token_id": 2,43 "feat_extract_activation": "gelu",44 "feat_extract_dropout": 0.0,45 "feat_extract_norm": "group",46 "feat_proj_dropout": 0.0,47 "feat_proj_layer_norm": true,48 "final_dropout": 0.1,49 "hidden_act": "gelu",50 "hidden_dropout": 0.1,51 "hidden_dropout_prob": 0.1,52 "hidden_size": 768,53 "initializer_range": 0.02,54 "intermediate_size": 3072,55 "layer_norm_eps": 1e-05,56 "layerdrop": 0.1,57 "mask_feature_length": 10,58 "mask_feature_min_masks": 0,59 "mask_feature_prob": 0.0,60 "mask_time_length": 10,61 "mask_time_min_masks": 2,62 "mask_time_prob": 0.05,63 "model_type": "hubert",64 "num_attention_heads": 12,65 "num_conv_pos_embedding_groups": 16,66 "num_conv_pos_embeddings": 128,67 "num_feat_extract_layers": 7,68 "num_hidden_layers": 12,69 "pad_token_id": 41,70 "tokenizer_class": "Wav2Vec2CTCTokenizer",71 "torch_dtype": "float32",72 "transformers_version": "4.17.0",73 "use_weighted_layer_sum": false,74 "vocab_size": 4275}76 