jonatasgrosman/wav2vec2-large-xlsr-53-japanese
8717.4m
1{2 "_name_or_path": "facebook/wav2vec2-large-xlsr-53",3 "activation_dropout": 0.05,4 "apply_spec_augment": true,5 "architectures": [6 "Wav2Vec2ForCTC"7 ],8 "attention_dropout": 0.1,9 "bos_token_id": 1,10 "conv_bias": true,11 "conv_dim": [12 512,13 512,14 512,15 512,16 512,17 512,18 51219 ],20 "conv_kernel": [21 10,22 3,23 3,24 3,25 3,26 2,27 228 ],29 "conv_stride": [30 5,31 2,32 2,33 2,34 2,35 2,36 237 ],38 "ctc_loss_reduction": "mean",39 "ctc_zero_infinity": true,40 "do_stable_layer_norm": true,41 "eos_token_id": 2,42 "feat_extract_activation": "gelu",43 "feat_extract_dropout": 0.0,44 "feat_extract_norm": "layer",45 "feat_proj_dropout": 0.05,46 "final_dropout": 0.0,47 "gradient_checkpointing": true,48 "hidden_act": "gelu",49 "hidden_dropout": 0.05,50 "hidden_size": 1024,51 "initializer_range": 0.02,52 "intermediate_size": 4096,53 "layer_norm_eps": 1e-05,54 "layerdrop": 0.05,55 "mask_channel_length": 10,56 "mask_channel_min_space": 1,57 "mask_channel_other": 0.0,58 "mask_channel_prob": 0.0,59 "mask_channel_selection": "static",60 "mask_feature_length": 10,61 "mask_feature_prob": 0.0,62 "mask_time_length": 10,63 "mask_time_min_space": 1,64 "mask_time_other": 0.0,65 "mask_time_prob": 0.05,66 "mask_time_selection": "static",67 "model_type": "wav2vec2",68 "num_attention_heads": 16,69 "num_conv_pos_embedding_groups": 16,70 "num_conv_pos_embeddings": 128,71 "num_feat_extract_layers": 7,72 "num_hidden_layers": 24,73 "pad_token_id": 0,74 "transformers_version": "4.5.0.dev0",75 "vocab_size": 234176}77 