Model save
Browse files- README.md +125 -0
- config.json +109 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +51 -0
- training_args.bin +3 -0
- vocab.json +34 -0
README.md
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base-960h
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Helldivers2ASR_V3
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Helldivers2ASR_V3
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 25.4595
|
| 22 |
+
- Wer: 0.0270
|
| 23 |
+
- Cer: 0.0107
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 6e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 60
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 58 |
+
| 1063.7894 | 1.0 | 114 | 718.9606 | 0.5828 | 0.3216 |
|
| 59 |
+
| 810.9251 | 2.0 | 228 | 524.2849 | 0.4911 | 0.2493 |
|
| 60 |
+
| 680.8981 | 3.0 | 342 | 421.2985 | 0.4214 | 0.2045 |
|
| 61 |
+
| 597.9041 | 4.0 | 456 | 366.2341 | 0.3686 | 0.1763 |
|
| 62 |
+
| 524.5883 | 5.0 | 570 | 305.7330 | 0.3089 | 0.1497 |
|
| 63 |
+
| 458.713 | 6.0 | 684 | 260.3347 | 0.2643 | 0.1275 |
|
| 64 |
+
| 406.8273 | 7.0 | 798 | 227.7853 | 0.2323 | 0.1076 |
|
| 65 |
+
| 378.9415 | 8.0 | 912 | 188.8116 | 0.1980 | 0.0934 |
|
| 66 |
+
| 336.5126 | 9.0 | 1026 | 165.1948 | 0.1691 | 0.0801 |
|
| 67 |
+
| 310.3794 | 10.0 | 1140 | 143.5318 | 0.1568 | 0.0721 |
|
| 68 |
+
| 285.877 | 11.0 | 1254 | 136.2682 | 0.1448 | 0.0670 |
|
| 69 |
+
| 274.0296 | 12.0 | 1368 | 122.3905 | 0.1298 | 0.0585 |
|
| 70 |
+
| 265.1471 | 13.0 | 1482 | 116.0494 | 0.1148 | 0.0531 |
|
| 71 |
+
| 221.5662 | 14.0 | 1596 | 105.7465 | 0.1075 | 0.0489 |
|
| 72 |
+
| 225.1541 | 15.0 | 1710 | 99.3887 | 0.1063 | 0.0477 |
|
| 73 |
+
| 201.7688 | 16.0 | 1824 | 91.4716 | 0.1017 | 0.0435 |
|
| 74 |
+
| 198.1517 | 17.0 | 1938 | 88.0316 | 0.0921 | 0.0405 |
|
| 75 |
+
| 182.0429 | 18.0 | 2052 | 86.2570 | 0.0898 | 0.0384 |
|
| 76 |
+
| 180.9772 | 19.0 | 2166 | 84.9040 | 0.0882 | 0.0399 |
|
| 77 |
+
| 176.9504 | 20.0 | 2280 | 70.6380 | 0.0743 | 0.0325 |
|
| 78 |
+
| 163.9662 | 21.0 | 2394 | 104.9963 | 0.0832 | 0.0426 |
|
| 79 |
+
| 165.1209 | 22.0 | 2508 | 64.8720 | 0.0747 | 0.0310 |
|
| 80 |
+
| 149.6314 | 23.0 | 2622 | 60.0919 | 0.0678 | 0.0288 |
|
| 81 |
+
| 156.3655 | 24.0 | 2736 | 63.2843 | 0.0643 | 0.0277 |
|
| 82 |
+
| 147.9974 | 25.0 | 2850 | 56.2312 | 0.0559 | 0.0246 |
|
| 83 |
+
| 132.3355 | 26.0 | 2964 | 58.3237 | 0.0535 | 0.0247 |
|
| 84 |
+
| 142.3996 | 27.0 | 3078 | 49.5403 | 0.0570 | 0.0221 |
|
| 85 |
+
| 124.0104 | 28.0 | 3192 | 45.3949 | 0.0505 | 0.0197 |
|
| 86 |
+
| 116.5822 | 29.0 | 3306 | 54.1334 | 0.0559 | 0.0225 |
|
| 87 |
+
| 119.3177 | 30.0 | 3420 | 45.9107 | 0.0489 | 0.0194 |
|
| 88 |
+
| 123.8109 | 31.0 | 3534 | 41.0828 | 0.0466 | 0.0179 |
|
| 89 |
+
| 118.6089 | 32.0 | 3648 | 41.0715 | 0.0447 | 0.0176 |
|
| 90 |
+
| 107.6029 | 33.0 | 3762 | 52.8643 | 0.0555 | 0.0217 |
|
| 91 |
+
| 113.0274 | 34.0 | 3876 | 36.1530 | 0.0458 | 0.0173 |
|
| 92 |
+
| 95.9924 | 35.0 | 3990 | 33.4645 | 0.0435 | 0.0158 |
|
| 93 |
+
| 102.7349 | 36.0 | 4104 | 36.7720 | 0.0455 | 0.0175 |
|
| 94 |
+
| 103.0268 | 37.0 | 4218 | 36.8673 | 0.0381 | 0.0163 |
|
| 95 |
+
| 96.3656 | 38.0 | 4332 | 35.1068 | 0.0420 | 0.0158 |
|
| 96 |
+
| 96.9253 | 39.0 | 4446 | 35.4023 | 0.0408 | 0.0164 |
|
| 97 |
+
| 95.3507 | 40.0 | 4560 | 31.9771 | 0.0378 | 0.0155 |
|
| 98 |
+
| 100.4609 | 41.0 | 4674 | 28.5974 | 0.0354 | 0.0134 |
|
| 99 |
+
| 95.2469 | 42.0 | 4788 | 35.2287 | 0.0401 | 0.0155 |
|
| 100 |
+
| 95.7411 | 43.0 | 4902 | 41.8120 | 0.0416 | 0.0176 |
|
| 101 |
+
| 87.7424 | 44.0 | 5016 | 27.3256 | 0.0320 | 0.0115 |
|
| 102 |
+
| 85.4531 | 45.0 | 5130 | 30.2653 | 0.0324 | 0.0127 |
|
| 103 |
+
| 84.8334 | 46.0 | 5244 | 29.6504 | 0.0335 | 0.0131 |
|
| 104 |
+
| 82.7842 | 47.0 | 5358 | 32.6864 | 0.0370 | 0.0150 |
|
| 105 |
+
| 80.188 | 48.0 | 5472 | 33.7373 | 0.0335 | 0.0145 |
|
| 106 |
+
| 88.2538 | 49.0 | 5586 | 32.3133 | 0.0343 | 0.0143 |
|
| 107 |
+
| 82.6046 | 50.0 | 5700 | 32.1506 | 0.0331 | 0.0134 |
|
| 108 |
+
| 89.6107 | 51.0 | 5814 | 30.5849 | 0.0331 | 0.0140 |
|
| 109 |
+
| 73.281 | 52.0 | 5928 | 25.5599 | 0.0312 | 0.0120 |
|
| 110 |
+
| 74.4069 | 53.0 | 6042 | 24.4939 | 0.0277 | 0.0106 |
|
| 111 |
+
| 72.1636 | 54.0 | 6156 | 24.1323 | 0.0285 | 0.0105 |
|
| 112 |
+
| 69.7004 | 55.0 | 6270 | 24.2016 | 0.0277 | 0.0105 |
|
| 113 |
+
| 83.1168 | 56.0 | 6384 | 24.9745 | 0.0300 | 0.0113 |
|
| 114 |
+
| 80.7796 | 57.0 | 6498 | 23.8529 | 0.0262 | 0.0103 |
|
| 115 |
+
| 80.1099 | 58.0 | 6612 | 28.6379 | 0.0300 | 0.0121 |
|
| 116 |
+
| 88.7483 | 59.0 | 6726 | 25.5322 | 0.0293 | 0.0110 |
|
| 117 |
+
| 76.292 | 60.0 | 6840 | 25.4595 | 0.0270 | 0.0107 |
|
| 118 |
+
|
| 119 |
+
|
| 120 |
+
### Framework versions
|
| 121 |
+
|
| 122 |
+
- Transformers 4.57.3
|
| 123 |
+
- Pytorch 2.5.1+cu121
|
| 124 |
+
- Datasets 3.6.0
|
| 125 |
+
- Tokenizers 0.22.1
|
config.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"adapter_attn_dim": null,
|
| 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": 0.15,
|
| 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 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "sum",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": false,
|
| 48 |
+
"dtype": "float32",
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "group",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.15,
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.15,
|
| 59 |
+
"hidden_dropout_prob": 0.1,
|
| 60 |
+
"hidden_size": 768,
|
| 61 |
+
"initializer_range": 0.02,
|
| 62 |
+
"intermediate_size": 3072,
|
| 63 |
+
"layer_norm_eps": 1e-05,
|
| 64 |
+
"layerdrop": 0.1,
|
| 65 |
+
"mask_feature_length": 10,
|
| 66 |
+
"mask_feature_min_masks": 0,
|
| 67 |
+
"mask_feature_prob": 0.0,
|
| 68 |
+
"mask_time_length": 10,
|
| 69 |
+
"mask_time_min_masks": 2,
|
| 70 |
+
"mask_time_prob": 0.05,
|
| 71 |
+
"model_type": "wav2vec2",
|
| 72 |
+
"num_adapter_layers": 3,
|
| 73 |
+
"num_attention_heads": 12,
|
| 74 |
+
"num_codevector_groups": 2,
|
| 75 |
+
"num_codevectors_per_group": 320,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 12,
|
| 80 |
+
"num_negatives": 100,
|
| 81 |
+
"output_hidden_size": 768,
|
| 82 |
+
"pad_token_id": 0,
|
| 83 |
+
"proj_codevector_dim": 256,
|
| 84 |
+
"tdnn_dilation": [
|
| 85 |
+
1,
|
| 86 |
+
2,
|
| 87 |
+
3,
|
| 88 |
+
1,
|
| 89 |
+
1
|
| 90 |
+
],
|
| 91 |
+
"tdnn_dim": [
|
| 92 |
+
512,
|
| 93 |
+
512,
|
| 94 |
+
512,
|
| 95 |
+
512,
|
| 96 |
+
1500
|
| 97 |
+
],
|
| 98 |
+
"tdnn_kernel": [
|
| 99 |
+
5,
|
| 100 |
+
3,
|
| 101 |
+
3,
|
| 102 |
+
1,
|
| 103 |
+
1
|
| 104 |
+
],
|
| 105 |
+
"transformers_version": "4.57.3",
|
| 106 |
+
"use_weighted_layer_sum": false,
|
| 107 |
+
"vocab_size": 32,
|
| 108 |
+
"xvector_output_dim": 512
|
| 109 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf613542b5abdfa629aefa0066abff26c1855d50fbe2d27e54c55a42c9dc702d
|
| 3 |
+
size 377611120
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": false,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"do_lower_case": false,
|
| 39 |
+
"do_normalize": true,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"extra_special_tokens": {},
|
| 42 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"processor_class": "Wav2Vec2Processor",
|
| 45 |
+
"replace_word_delimiter_char": " ",
|
| 46 |
+
"return_attention_mask": false,
|
| 47 |
+
"target_lang": null,
|
| 48 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 49 |
+
"unk_token": "<unk>",
|
| 50 |
+
"word_delimiter_token": "|"
|
| 51 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d5952ce65efa4dfc7d5743559aa2373756d8171e3cf43c74f5abe714004040b
|
| 3 |
+
size 5432
|
vocab.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"'": 27,
|
| 3 |
+
"</s>": 2,
|
| 4 |
+
"<pad>": 0,
|
| 5 |
+
"<s>": 1,
|
| 6 |
+
"<unk>": 3,
|
| 7 |
+
"A": 7,
|
| 8 |
+
"B": 24,
|
| 9 |
+
"C": 19,
|
| 10 |
+
"D": 14,
|
| 11 |
+
"E": 5,
|
| 12 |
+
"F": 20,
|
| 13 |
+
"G": 21,
|
| 14 |
+
"H": 11,
|
| 15 |
+
"I": 10,
|
| 16 |
+
"J": 29,
|
| 17 |
+
"K": 26,
|
| 18 |
+
"L": 15,
|
| 19 |
+
"M": 17,
|
| 20 |
+
"N": 9,
|
| 21 |
+
"O": 8,
|
| 22 |
+
"P": 23,
|
| 23 |
+
"Q": 30,
|
| 24 |
+
"R": 13,
|
| 25 |
+
"S": 12,
|
| 26 |
+
"T": 6,
|
| 27 |
+
"U": 16,
|
| 28 |
+
"V": 25,
|
| 29 |
+
"W": 18,
|
| 30 |
+
"X": 28,
|
| 31 |
+
"Y": 22,
|
| 32 |
+
"Z": 31,
|
| 33 |
+
"|": 4
|
| 34 |
+
}
|