yesj1234 commited on
Commit
a6d0635
1 Parent(s): 38c698a

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-xlsr-53
4
+ tags:
5
+ - automatic-speech-recognition
6
+ - ./sample_speech.py
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: ko-xlsr
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # ko-xlsr
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ./SAMPLE_SPEECH.PY - NA dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5172
21
+ - Cer: 0.1076
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 64
48
+ - total_eval_batch_size: 8
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 1000
52
+ - num_epochs: 40
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
58
+ | 6.742 | 2.6 | 1500 | 0.9038 | 0.2330 |
59
+ | 0.9228 | 5.2 | 3000 | 0.6193 | 0.1656 |
60
+ | 0.6805 | 7.8 | 4500 | 0.5522 | 0.1481 |
61
+ | 0.5577 | 10.4 | 6000 | 0.5136 | 0.1349 |
62
+ | 0.4797 | 13.0 | 7500 | 0.5074 | 0.1312 |
63
+ | 0.4161 | 15.6 | 9000 | 0.4959 | 0.1243 |
64
+ | 0.3701 | 18.21 | 10500 | 0.4948 | 0.1224 |
65
+ | 0.3307 | 20.81 | 12000 | 0.4881 | 0.1199 |
66
+ | 0.2946 | 23.41 | 13500 | 0.4970 | 0.1179 |
67
+ | 0.2636 | 26.01 | 15000 | 0.4950 | 0.1145 |
68
+ | 0.2367 | 28.61 | 16500 | 0.4905 | 0.1119 |
69
+ | 0.2157 | 31.21 | 18000 | 0.5066 | 0.1110 |
70
+ | 0.1979 | 33.81 | 19500 | 0.5133 | 0.1103 |
71
+ | 0.1808 | 36.41 | 21000 | 0.5160 | 0.1091 |
72
+ | 0.17 | 39.01 | 22500 | 0.5129 | 0.1074 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.34.0
78
+ - Pytorch 2.0.1+cu117
79
+ - Datasets 2.14.5
80
+ - Tokenizers 0.14.0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 1438,
3
+ "<s>": 1437,
4
+ "[PAD]": 1436,
5
+ "[UNK]": 1435
6
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 39.95,
3
+ "eval_cer": 0.10764723995306297,
4
+ "eval_loss": 0.5172480344772339,
5
+ "eval_runtime": 199.9485,
6
+ "eval_samples": 4606,
7
+ "eval_samples_per_second": 23.036,
8
+ "eval_steps_per_second": 2.881,
9
+ "train_loss": 0.7889066434568829,
10
+ "train_runtime": 39248.6958,
11
+ "train_samples": 36905,
12
+ "train_samples_per_second": 37.611,
13
+ "train_steps_per_second": 0.587
14
+ }
checkpoint-22500/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 1438,
3
+ "<s>": 1437,
4
+ "[PAD]": 1436,
5
+ "[UNK]": 1435
6
+ }
checkpoint-22500/config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.05,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.05,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 1436,
90
+ "proj_codevector_dim": 768,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.34.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 1439,
116
+ "xvector_output_dim": 512
117
+ }
checkpoint-22500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdfa3e86b791ad545830b0c1eecd4ffcae5b2b956ea81f9a951f436bed95b04
3
+ size 2501959105
checkpoint-22500/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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-22500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399bb59ee63296e22bce596beb02cff21a9cff1c0ddd5725aa7ca40eb27b7eab
3
+ size 1267801773
checkpoint-22500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aacc8ba77b6d79def5207d0c9f656f52a172edabb3234c460b386c462a73941
3
+ size 17719
checkpoint-22500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f04256badec6e7c177629e24b77990bf32f2bfdec39daa9dad2af64766a0877
3
+ size 17655
checkpoint-22500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412dfcf221238de34e551e7d43a8dbebe47d3f391641b71fa99ee9fc719f70eb
3
+ size 17655
checkpoint-22500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9c14c070370c5c49e99b8a747cbc67d8d2e13136f2756752fb98cdadb1ff23
3
+ size 17655
checkpoint-22500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee054f9d0b5d673b80e6bb4b13311a5bc8fb6149d9a68341ac99cb734c2b12c
3
+ size 627
checkpoint-22500/special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "</s>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "pad_token": "[PAD]",
9
+ "unk_token": "[UNK]"
10
+ }
checkpoint-22500/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1435": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1436": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "1437": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "1438": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [
37
+ "<s>",
38
+ "</s>"
39
+ ],
40
+ "bos_token": "<s>",
41
+ "clean_up_tokenization_spaces": true,
42
+ "config": null,
43
+ "do_lower_case": false,
44
+ "eos_token": "</s>",
45
+ "model_max_length": 1000000000000000019884624838656,
46
+ "pad_token": "[PAD]",
47
+ "processor_class": "Wav2Vec2Processor",
48
+ "replace_word_delimiter_char": " ",
49
+ "target_lang": null,
50
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
51
+ "tokenizer_file": null,
52
+ "tokenizer_type": "wav2vec2",
53
+ "trust_remote_code": false,
54
+ "unk_token": "[UNK]",
55
+ "word_delimiter_token": "|"
56
+ }
checkpoint-22500/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 39.01170351105332,
5
+ "eval_steps": 1500,
6
+ "global_step": 22500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.6,
13
+ "learning_rate": 0.0002932622504537205,
14
+ "loss": 6.742,
15
+ "step": 1500
16
+ },
17
+ {
18
+ "epoch": 2.6,
19
+ "eval_cer": 0.2330206972312148,
20
+ "eval_loss": 0.9037942886352539,
21
+ "eval_runtime": 202.8675,
22
+ "eval_samples_per_second": 22.704,
23
+ "eval_steps_per_second": 2.839,
24
+ "step": 1500
25
+ },
26
+ {
27
+ "epoch": 5.2,
28
+ "learning_rate": 0.00027284482758620687,
29
+ "loss": 0.9228,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 5.2,
34
+ "eval_cer": 0.1655612053827781,
35
+ "eval_loss": 0.6193090677261353,
36
+ "eval_runtime": 202.6276,
37
+ "eval_samples_per_second": 22.731,
38
+ "eval_steps_per_second": 2.843,
39
+ "step": 3000
40
+ },
41
+ {
42
+ "epoch": 7.8,
43
+ "learning_rate": 0.00025242740471869324,
44
+ "loss": 0.6805,
45
+ "step": 4500
46
+ },
47
+ {
48
+ "epoch": 7.8,
49
+ "eval_cer": 0.14813458609698654,
50
+ "eval_loss": 0.5522382259368896,
51
+ "eval_runtime": 201.9891,
52
+ "eval_samples_per_second": 22.803,
53
+ "eval_steps_per_second": 2.852,
54
+ "step": 4500
55
+ },
56
+ {
57
+ "epoch": 10.4,
58
+ "learning_rate": 0.00023200998185117966,
59
+ "loss": 0.5577,
60
+ "step": 6000
61
+ },
62
+ {
63
+ "epoch": 10.4,
64
+ "eval_cer": 0.1348940171935986,
65
+ "eval_loss": 0.5135979652404785,
66
+ "eval_runtime": 208.2736,
67
+ "eval_samples_per_second": 22.115,
68
+ "eval_steps_per_second": 2.766,
69
+ "step": 6000
70
+ },
71
+ {
72
+ "epoch": 13.0,
73
+ "learning_rate": 0.00021160617059891106,
74
+ "loss": 0.4797,
75
+ "step": 7500
76
+ },
77
+ {
78
+ "epoch": 13.0,
79
+ "eval_cer": 0.1312322633799652,
80
+ "eval_loss": 0.5074160099029541,
81
+ "eval_runtime": 207.3615,
82
+ "eval_samples_per_second": 22.212,
83
+ "eval_steps_per_second": 2.778,
84
+ "step": 7500
85
+ },
86
+ {
87
+ "epoch": 15.6,
88
+ "learning_rate": 0.00019120235934664247,
89
+ "loss": 0.4161,
90
+ "step": 9000
91
+ },
92
+ {
93
+ "epoch": 15.6,
94
+ "eval_cer": 0.12432486414061135,
95
+ "eval_loss": 0.4958959221839905,
96
+ "eval_runtime": 198.4858,
97
+ "eval_samples_per_second": 23.206,
98
+ "eval_steps_per_second": 2.902,
99
+ "step": 9000
100
+ },
101
+ {
102
+ "epoch": 18.21,
103
+ "learning_rate": 0.00017078493647912883,
104
+ "loss": 0.3701,
105
+ "step": 10500
106
+ },
107
+ {
108
+ "epoch": 18.21,
109
+ "eval_cer": 0.12240244338845382,
110
+ "eval_loss": 0.4947836697101593,
111
+ "eval_runtime": 198.4077,
112
+ "eval_samples_per_second": 23.215,
113
+ "eval_steps_per_second": 2.903,
114
+ "step": 10500
115
+ },
116
+ {
117
+ "epoch": 20.81,
118
+ "learning_rate": 0.00015038112522686024,
119
+ "loss": 0.3307,
120
+ "step": 12000
121
+ },
122
+ {
123
+ "epoch": 20.81,
124
+ "eval_cer": 0.11993908173200955,
125
+ "eval_loss": 0.48810431361198425,
126
+ "eval_runtime": 197.2477,
127
+ "eval_samples_per_second": 23.351,
128
+ "eval_steps_per_second": 2.92,
129
+ "step": 12000
130
+ },
131
+ {
132
+ "epoch": 23.41,
133
+ "learning_rate": 0.00012996370235934663,
134
+ "loss": 0.2946,
135
+ "step": 13500
136
+ },
137
+ {
138
+ "epoch": 23.41,
139
+ "eval_cer": 0.1179251171345112,
140
+ "eval_loss": 0.4970262050628662,
141
+ "eval_runtime": 201.6098,
142
+ "eval_samples_per_second": 22.846,
143
+ "eval_steps_per_second": 2.857,
144
+ "step": 13500
145
+ },
146
+ {
147
+ "epoch": 26.01,
148
+ "learning_rate": 0.00010954627949183302,
149
+ "loss": 0.2636,
150
+ "step": 15000
151
+ },
152
+ {
153
+ "epoch": 26.01,
154
+ "eval_cer": 0.11448806185035078,
155
+ "eval_loss": 0.4949529767036438,
156
+ "eval_runtime": 204.2568,
157
+ "eval_samples_per_second": 22.55,
158
+ "eval_steps_per_second": 2.82,
159
+ "step": 15000
160
+ },
161
+ {
162
+ "epoch": 28.61,
163
+ "learning_rate": 8.915607985480944e-05,
164
+ "loss": 0.2367,
165
+ "step": 16500
166
+ },
167
+ {
168
+ "epoch": 28.61,
169
+ "eval_cer": 0.11192483418080741,
170
+ "eval_loss": 0.49051955342292786,
171
+ "eval_runtime": 200.659,
172
+ "eval_samples_per_second": 22.954,
173
+ "eval_steps_per_second": 2.871,
174
+ "step": 16500
175
+ },
176
+ {
177
+ "epoch": 31.21,
178
+ "learning_rate": 6.875226860254083e-05,
179
+ "loss": 0.2157,
180
+ "step": 18000
181
+ },
182
+ {
183
+ "epoch": 31.21,
184
+ "eval_cer": 0.11102604006291558,
185
+ "eval_loss": 0.5065664649009705,
186
+ "eval_runtime": 198.3314,
187
+ "eval_samples_per_second": 23.224,
188
+ "eval_steps_per_second": 2.904,
189
+ "step": 18000
190
+ },
191
+ {
192
+ "epoch": 33.81,
193
+ "learning_rate": 4.833484573502722e-05,
194
+ "loss": 0.1979,
195
+ "step": 19500
196
+ },
197
+ {
198
+ "epoch": 33.81,
199
+ "eval_cer": 0.11034362230673846,
200
+ "eval_loss": 0.5133121609687805,
201
+ "eval_runtime": 198.0306,
202
+ "eval_samples_per_second": 23.259,
203
+ "eval_steps_per_second": 2.909,
204
+ "step": 19500
205
+ },
206
+ {
207
+ "epoch": 36.41,
208
+ "learning_rate": 2.791742286751361e-05,
209
+ "loss": 0.1808,
210
+ "step": 21000
211
+ },
212
+ {
213
+ "epoch": 36.41,
214
+ "eval_cer": 0.10908697497524156,
215
+ "eval_loss": 0.516022801399231,
216
+ "eval_runtime": 198.8874,
217
+ "eval_samples_per_second": 23.159,
218
+ "eval_steps_per_second": 2.896,
219
+ "step": 21000
220
+ },
221
+ {
222
+ "epoch": 39.01,
223
+ "learning_rate": 7.527223230490017e-06,
224
+ "loss": 0.17,
225
+ "step": 22500
226
+ },
227
+ {
228
+ "epoch": 39.01,
229
+ "eval_cer": 0.10736428624928221,
230
+ "eval_loss": 0.5128792524337769,
231
+ "eval_runtime": 200.4673,
232
+ "eval_samples_per_second": 22.976,
233
+ "eval_steps_per_second": 2.873,
234
+ "step": 22500
235
+ }
236
+ ],
237
+ "logging_steps": 1500,
238
+ "max_steps": 23040,
239
+ "num_train_epochs": 40,
240
+ "save_steps": 1500,
241
+ "total_flos": 1.6536314253048755e+20,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }
checkpoint-22500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84fd5eecba213b71cf981134653cb7eabfffd55d4675b8e4237fa1cee57c8e6
3
+ size 4027
checkpoint-22500/vocab.json ADDED
@@ -0,0 +1,1439 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 1,
3
+ "0": 2,
4
+ "1": 3,
5
+ "2": 4,
6
+ "3": 5,
7
+ "4": 6,
8
+ "5": 7,
9
+ "6": 8,
10
+ "7": 9,
11
+ "8": 10,
12
+ "9": 11,
13
+ "[PAD]": 1436,
14
+ "[UNK]": 1435,
15
+ "a": 12,
16
+ "b": 13,
17
+ "c": 14,
18
+ "d": 15,
19
+ "e": 16,
20
+ "f": 17,
21
+ "g": 18,
22
+ "h": 19,
23
+ "i": 20,
24
+ "j": 21,
25
+ "k": 22,
26
+ "l": 23,
27
+ "m": 24,
28
+ "n": 25,
29
+ "o": 26,
30
+ "p": 27,
31
+ "q": 28,
32
+ "r": 29,
33
+ "s": 30,
34
+ "t": 31,
35
+ "u": 32,
36
+ "v": 33,
37
+ "w": 34,
38
+ "x": 35,
39
+ "y": 36,
40
+ "z": 37,
41
+ "|": 0,
42
+ "}": 38,
43
+ "ㅋ": 39,
44
+ "ㅡ": 40,
45
+ "가": 41,
46
+ "각": 42,
47
+ "간": 43,
48
+ "갇": 44,
49
+ "갈": 45,
50
+ "감": 46,
51
+ "갑": 47,
52
+ "값": 48,
53
+ "갓": 49,
54
+ "갔": 50,
55
+ "강": 51,
56
+ "갖": 52,
57
+ "같": 53,
58
+ "갛": 54,
59
+ "개": 55,
60
+ "객": 56,
61
+ "갠": 57,
62
+ "갤": 58,
63
+ "갬": 59,
64
+ "갭": 60,
65
+ "갯": 61,
66
+ "갰": 62,
67
+ "갱": 63,
68
+ "걀": 64,
69
+ "걍": 65,
70
+ "걔": 66,
71
+ "걘": 67,
72
+ "거": 68,
73
+ "걱": 69,
74
+ "건": 70,
75
+ "걷": 71,
76
+ "걸": 72,
77
+ "검": 73,
78
+ "겁": 74,
79
+ "것": 75,
80
+ "겅": 76,
81
+ "겉": 77,
82
+ "겋": 78,
83
+ "게": 79,
84
+ "겐": 80,
85
+ "겔": 81,
86
+ "겟": 82,
87
+ "겠": 83,
88
+ "겨": 84,
89
+ "격": 85,
90
+ "겪": 86,
91
+ "견": 87,
92
+ "결": 88,
93
+ "겸": 89,
94
+ "겹": 90,
95
+ "겼": 91,
96
+ "경": 92,
97
+ "곁": 93,
98
+ "계": 94,
99
+ "고": 95,
100
+ "곡": 96,
101
+ "곤": 97,
102
+ "곧": 98,
103
+ "골": 99,
104
+ "곰": 100,
105
+ "곱": 101,
106
+ "곳": 102,
107
+ "공": 103,
108
+ "곶": 104,
109
+ "과": 105,
110
+ "관": 106,
111
+ "괄": 107,
112
+ "괍": 108,
113
+ "광": 109,
114
+ "괘": 110,
115
+ "괜": 111,
116
+ "괞": 112,
117
+ "괴": 113,
118
+ "굉": 114,
119
+ "교": 115,
120
+ "굔": 116,
121
+ "구": 117,
122
+ "국": 118,
123
+ "군": 119,
124
+ "굳": 120,
125
+ "굴": 121,
126
+ "굵": 122,
127
+ "굶": 123,
128
+ "굽": 124,
129
+ "굿": 125,
130
+ "궁": 126,
131
+ "궈": 127,
132
+ "권": 128,
133
+ "궜": 129,
134
+ "귀": 130,
135
+ "귓": 131,
136
+ "규": 132,
137
+ "균": 133,
138
+ "귤": 134,
139
+ "그": 135,
140
+ "극": 136,
141
+ "근": 137,
142
+ "글": 138,
143
+ "긁": 139,
144
+ "금": 140,
145
+ "급": 141,
146
+ "긋": 142,
147
+ "긍": 143,
148
+ "기": 144,
149
+ "긴": 145,
150
+ "길": 146,
151
+ "김": 147,
152
+ "깁": 148,
153
+ "깃": 149,
154
+ "깉": 150,
155
+ "깊": 151,
156
+ "까": 152,
157
+ "깐": 153,
158
+ "깔": 154,
159
+ "깜": 155,
160
+ "깝": 156,
161
+ "깠": 157,
162
+ "깡": 158,
163
+ "깥": 159,
164
+ "깨": 160,
165
+ "깬": 161,
166
+ "깻": 162,
167
+ "깼": 163,
168
+ "꺼": 164,
169
+ "꺽": 165,
170
+ "껀": 166,
171
+ "껄": 167,
172
+ "껌": 168,
173
+ "껍": 169,
174
+ "껏": 170,
175
+ "껐": 171,
176
+ "껑": 172,
177
+ "께": 173,
178
+ "껴": 174,
179
+ "꼈": 175,
180
+ "꼐": 176,
181
+ "꼬": 177,
182
+ "꼭": 178,
183
+ "꼴": 179,
184
+ "꼼": 180,
185
+ "꼽": 181,
186
+ "꽁": 182,
187
+ "꽂": 183,
188
+ "꽃": 184,
189
+ "꽉": 185,
190
+ "꽝": 186,
191
+ "꽤": 187,
192
+ "꾸": 188,
193
+ "꾹": 189,
194
+ "꾼": 190,
195
+ "꿀": 191,
196
+ "꿈": 192,
197
+ "꿉": 193,
198
+ "꿍": 194,
199
+ "꿔": 195,
200
+ "꿨": 196,
201
+ "뀌": 197,
202
+ "뀐": 198,
203
+ "뀔": 199,
204
+ "뀝": 200,
205
+ "끄": 201,
206
+ "끈": 202,
207
+ "끊": 203,
208
+ "끌": 204,
209
+ "끓": 205,
210
+ "끔": 206,
211
+ "끗": 207,
212
+ "끝": 208,
213
+ "끼": 209,
214
+ "끽": 210,
215
+ "낀": 211,
216
+ "낄": 212,
217
+ "낌": 213,
218
+ "낍": 214,
219
+ "낑": 215,
220
+ "나": 216,
221
+ "낙": 217,
222
+ "낚": 218,
223
+ "난": 219,
224
+ "날": 220,
225
+ "낡": 221,
226
+ "남": 222,
227
+ "납": 223,
228
+ "낫": 224,
229
+ "났": 225,
230
+ "낭": 226,
231
+ "낮": 227,
232
+ "낯": 228,
233
+ "낱": 229,
234
+ "낳": 230,
235
+ "내": 231,
236
+ "낵": 232,
237
+ "낸": 233,
238
+ "낼": 234,
239
+ "냄": 235,
240
+ "냅": 236,
241
+ "냇": 237,
242
+ "냈": 238,
243
+ "냉": 239,
244
+ "냐": 240,
245
+ "냠": 241,
246
+ "냥": 242,
247
+ "너": 243,
248
+ "넉": 244,
249
+ "넌": 245,
250
+ "널": 246,
251
+ "넓": 247,
252
+ "넘": 248,
253
+ "넙": 249,
254
+ "넛": 250,
255
+ "넣": 251,
256
+ "네": 252,
257
+ "넨": 253,
258
+ "넷": 254,
259
+ "녀": 255,
260
+ "녁": 256,
261
+ "년": 257,
262
+ "념": 258,
263
+ "녔": 259,
264
+ "녕": 260,
265
+ "노": 261,
266
+ "녹": 262,
267
+ "논": 263,
268
+ "놀": 264,
269
+ "놈": 265,
270
+ "농": 266,
271
+ "높": 267,
272
+ "놓": 268,
273
+ "놔": 269,
274
+ "놨": 270,
275
+ "뇌": 271,
276
+ "뇨": 272,
277
+ "누": 273,
278
+ "눅": 274,
279
+ "눈": 275,
280
+ "눌": 276,
281
+ "눔": 277,
282
+ "눠": 278,
283
+ "눴": 279,
284
+ "뉘": 280,
285
+ "뉜": 281,
286
+ "뉩": 282,
287
+ "뉴": 283,
288
+ "느": 284,
289
+ "는": 285,
290
+ "늘": 286,
291
+ "늙": 287,
292
+ "능": 288,
293
+ "늦": 289,
294
+ "늬": 290,
295
+ "니": 291,
296
+ "닉": 292,
297
+ "닌": 293,
298
+ "닐": 294,
299
+ "님": 295,
300
+ "닙": 296,
301
+ "닝": 297,
302
+ "다": 298,
303
+ "닥": 299,
304
+ "닦": 300,
305
+ "단": 301,
306
+ "닫": 302,
307
+ "달": 303,
308
+ "닭": 304,
309
+ "닮": 305,
310
+ "닳": 306,
311
+ "담": 307,
312
+ "답": 308,
313
+ "닷": 309,
314
+ "당": 310,
315
+ "닿": 311,
316
+ "대": 312,
317
+ "댁": 313,
318
+ "댄": 314,
319
+ "댈": 315,
320
+ "댑": 316,
321
+ "댓": 317,
322
+ "댔": 318,
323
+ "댕": 319,
324
+ "댗": 320,
325
+ "댜": 321,
326
+ "더": 322,
327
+ "덕": 323,
328
+ "던": 324,
329
+ "덜": 325,
330
+ "덟": 326,
331
+ "덤": 327,
332
+ "덥": 328,
333
+ "덧": 329,
334
+ "덩": 330,
335
+ "덮": 331,
336
+ "데": 332,
337
+ "델": 333,
338
+ "뎁": 334,
339
+ "뎅": 335,
340
+ "도": 336,
341
+ "독": 337,
342
+ "돈": 338,
343
+ "돋": 339,
344
+ "돌": 340,
345
+ "돕": 341,
346
+ "돗": 342,
347
+ "동": 343,
348
+ "돼": 344,
349
+ "됐": 345,
350
+ "되": 346,
351
+ "된": 347,
352
+ "될": 348,
353
+ "됨": 349,
354
+ "됩": 350,
355
+ "두": 351,
356
+ "둑": 352,
357
+ "둔": 353,
358
+ "둘": 354,
359
+ "둠": 355,
360
+ "둡": 356,
361
+ "둣": 357,
362
+ "둥": 358,
363
+ "둬": 359,
364
+ "뒀": 360,
365
+ "뒤": 361,
366
+ "뒷": 362,
367
+ "듕": 363,
368
+ "드": 364,
369
+ "득": 365,
370
+ "든": 366,
371
+ "듣": 367,
372
+ "들": 368,
373
+ "듦": 369,
374
+ "듬": 370,
375
+ "듭": 371,
376
+ "듯": 372,
377
+ "등": 373,
378
+ "디": 374,
379
+ "딘": 375,
380
+ "딜": 376,
381
+ "딥": 377,
382
+ "딨": 378,
383
+ "딩": 379,
384
+ "딪": 380,
385
+ "따": 381,
386
+ "딱": 382,
387
+ "딴": 383,
388
+ "딸": 384,
389
+ "땀": 385,
390
+ "땄": 386,
391
+ "땅": 387,
392
+ "땋": 388,
393
+ "때": 389,
394
+ "땐": 390,
395
+ "땜": 391,
396
+ "땠": 392,
397
+ "땡": 393,
398
+ "떄": 394,
399
+ "떙": 395,
400
+ "떠": 396,
401
+ "떡": 397,
402
+ "떢": 398,
403
+ "떤": 399,
404
+ "떨": 400,
405
+ "떫": 401,
406
+ "떳": 402,
407
+ "떴": 403,
408
+ "떵": 404,
409
+ "떻": 405,
410
+ "떼": 406,
411
+ "뗄": 407,
412
+ "뗐": 408,
413
+ "또": 409,
414
+ "똑": 410,
415
+ "똠": 411,
416
+ "똥": 412,
417
+ "뚜": 413,
418
+ "뚝": 414,
419
+ "뚤": 415,
420
+ "뚫": 416,
421
+ "뚱": 417,
422
+ "뛰": 418,
423
+ "뛸": 419,
424
+ "뜨": 420,
425
+ "뜩": 421,
426
+ "뜬": 422,
427
+ "뜯": 423,
428
+ "뜰": 424,
429
+ "뜸": 425,
430
+ "뜹": 426,
431
+ "뜻": 427,
432
+ "띄": 428,
433
+ "띈": 429,
434
+ "띠": 430,
435
+ "띡": 431,
436
+ "띵": 432,
437
+ "라": 433,
438
+ "락": 434,
439
+ "란": 435,
440
+ "랄": 436,
441
+ "람": 437,
442
+ "랍": 438,
443
+ "랐": 439,
444
+ "랑": 440,
445
+ "랖": 441,
446
+ "랗": 442,
447
+ "래": 443,
448
+ "랙": 444,
449
+ "랜": 445,
450
+ "랠": 446,
451
+ "램": 447,
452
+ "랩": 448,
453
+ "랫": 449,
454
+ "랬": 450,
455
+ "랭": 451,
456
+ "략": 452,
457
+ "량": 453,
458
+ "러": 454,
459
+ "럭": 455,
460
+ "런": 456,
461
+ "럴": 457,
462
+ "럼": 458,
463
+ "럽": 459,
464
+ "렀": 460,
465
+ "렁": 461,
466
+ "렇": 462,
467
+ "레": 463,
468
+ "렉": 464,
469
+ "렌": 465,
470
+ "렐": 466,
471
+ "렘": 467,
472
+ "려": 468,
473
+ "력": 469,
474
+ "련": 470,
475
+ "렬": 471,
476
+ "렴": 472,
477
+ "렵": 473,
478
+ "렸": 474,
479
+ "령": 475,
480
+ "렿": 476,
481
+ "례": 477,
482
+ "로": 478,
483
+ "록": 479,
484
+ "론": 480,
485
+ "롤": 481,
486
+ "롬": 482,
487
+ "롭": 483,
488
+ "롯": 484,
489
+ "롱": 485,
490
+ "롷": 486,
491
+ "뢰": 487,
492
+ "료": 488,
493
+ "룡": 489,
494
+ "루": 490,
495
+ "룩": 491,
496
+ "룰": 492,
497
+ "룽": 493,
498
+ "뤄": 494,
499
+ "류": 495,
500
+ "륙": 496,
501
+ "률": 497,
502
+ "륨": 498,
503
+ "륭": 499,
504
+ "르": 500,
505
+ "륵": 501,
506
+ "른": 502,
507
+ "를": 503,
508
+ "름": 504,
509
+ "릅": 505,
510
+ "릇": 506,
511
+ "릉": 507,
512
+ "릎": 508,
513
+ "리": 509,
514
+ "릭": 510,
515
+ "린": 511,
516
+ "릴": 512,
517
+ "림": 513,
518
+ "립": 514,
519
+ "릿": 515,
520
+ "링": 516,
521
+ "마": 517,
522
+ "막": 518,
523
+ "만": 519,
524
+ "많": 520,
525
+ "말": 521,
526
+ "맑": 522,
527
+ "맘": 523,
528
+ "맙": 524,
529
+ "맛": 525,
530
+ "망": 526,
531
+ "맞": 527,
532
+ "맡": 528,
533
+ "맣": 529,
534
+ "매": 530,
535
+ "맥": 531,
536
+ "맨": 532,
537
+ "맴": 533,
538
+ "맵": 534,
539
+ "맸": 535,
540
+ "맹": 536,
541
+ "머": 537,
542
+ "먹": 538,
543
+ "먼": 539,
544
+ "멀": 540,
545
+ "멈": 541,
546
+ "멋": 542,
547
+ "멍": 543,
548
+ "메": 544,
549
+ "멕": 545,
550
+ "멘": 546,
551
+ "멜": 547,
552
+ "멤": 548,
553
+ "며": 549,
554
+ "면": 550,
555
+ "멸": 551,
556
+ "명": 552,
557
+ "몇": 553,
558
+ "모": 554,
559
+ "목": 555,
560
+ "몫": 556,
561
+ "몬": 557,
562
+ "몰": 558,
563
+ "몸": 559,
564
+ "몹": 560,
565
+ "못": 561,
566
+ "몽": 562,
567
+ "묘": 563,
568
+ "무": 564,
569
+ "묵": 565,
570
+ "묶": 566,
571
+ "문": 567,
572
+ "묻": 568,
573
+ "물": 569,
574
+ "묽": 570,
575
+ "뭇": 571,
576
+ "뭉": 572,
577
+ "뭐": 573,
578
+ "뭔": 574,
579
+ "뭘": 575,
580
+ "뭡": 576,
581
+ "뮤": 577,
582
+ "므": 578,
583
+ "믄": 579,
584
+ "믈": 580,
585
+ "믐": 581,
586
+ "미": 582,
587
+ "믹": 583,
588
+ "민": 584,
589
+ "믾": 585,
590
+ "믿": 586,
591
+ "밀": 587,
592
+ "밌": 588,
593
+ "밍": 589,
594
+ "및": 590,
595
+ "밑": 591,
596
+ "바": 592,
597
+ "박": 593,
598
+ "밖": 594,
599
+ "반": 595,
600
+ "받": 596,
601
+ "발": 597,
602
+ "밝": 598,
603
+ "밟": 599,
604
+ "밤": 600,
605
+ "밥": 601,
606
+ "밧": 602,
607
+ "방": 603,
608
+ "밭": 604,
609
+ "배": 605,
610
+ "백": 606,
611
+ "밴": 607,
612
+ "밸": 608,
613
+ "뱄": 609,
614
+ "뱅": 610,
615
+ "뱉": 611,
616
+ "버": 612,
617
+ "벅": 613,
618
+ "번": 614,
619
+ "벌": 615,
620
+ "범": 616,
621
+ "법": 617,
622
+ "벗": 618,
623
+ "벚": 619,
624
+ "베": 620,
625
+ "벡": 621,
626
+ "벤": 622,
627
+ "벨": 623,
628
+ "벳": 624,
629
+ "벼": 625,
630
+ "벽": 626,
631
+ "변": 627,
632
+ "별": 628,
633
+ "볍": 629,
634
+ "병": 630,
635
+ "볕": 631,
636
+ "보": 632,
637
+ "복": 633,
638
+ "볶": 634,
639
+ "본": 635,
640
+ "볼": 636,
641
+ "봄": 637,
642
+ "봅": 638,
643
+ "봉": 639,
644
+ "봐": 640,
645
+ "봤": 641,
646
+ "봬": 642,
647
+ "봽": 643,
648
+ "뵀": 644,
649
+ "뵈": 645,
650
+ "뵌": 646,
651
+ "뵐": 647,
652
+ "뵙": 648,
653
+ "뵬": 649,
654
+ "뵹": 650,
655
+ "부": 651,
656
+ "북": 652,
657
+ "분": 653,
658
+ "불": 654,
659
+ "붉": 655,
660
+ "붓": 656,
661
+ "붕": 657,
662
+ "붙": 658,
663
+ "붚": 659,
664
+ "뷔": 660,
665
+ "뷰": 661,
666
+ "브": 662,
667
+ "블": 663,
668
+ "비": 664,
669
+ "빈": 665,
670
+ "빔": 666,
671
+ "빗": 667,
672
+ "빙": 668,
673
+ "빛": 669,
674
+ "빠": 670,
675
+ "빡": 671,
676
+ "빨": 672,
677
+ "빴": 673,
678
+ "빵": 674,
679
+ "빼": 675,
680
+ "뺄": 676,
681
+ "뺏": 677,
682
+ "뺐": 678,
683
+ "뺴": 679,
684
+ "뻐": 680,
685
+ "뻑": 681,
686
+ "뻔": 682,
687
+ "뻗": 683,
688
+ "뻘": 684,
689
+ "뻣": 685,
690
+ "뻥": 686,
691
+ "뼈": 687,
692
+ "뽀": 688,
693
+ "뽁": 689,
694
+ "뽂": 690,
695
+ "���": 691,
696
+ "뽕": 692,
697
+ "뾰": 693,
698
+ "뿅": 694,
699
+ "뿌": 695,
700
+ "뿍": 696,
701
+ "뿐": 697,
702
+ "뿔": 698,
703
+ "뿜": 699,
704
+ "뿝": 700,
705
+ "쁘": 701,
706
+ "쁜": 702,
707
+ "쁠": 703,
708
+ "쁨": 704,
709
+ "쁩": 705,
710
+ "삐": 706,
711
+ "삑": 707,
712
+ "사": 708,
713
+ "삭": 709,
714
+ "산": 710,
715
+ "살": 711,
716
+ "삶": 712,
717
+ "삼": 713,
718
+ "삽": 714,
719
+ "삿": 715,
720
+ "샀": 716,
721
+ "상": 717,
722
+ "새": 718,
723
+ "색": 719,
724
+ "샌": 720,
725
+ "샘": 721,
726
+ "샛": 722,
727
+ "생": 723,
728
+ "샤": 724,
729
+ "샥": 725,
730
+ "샬": 726,
731
+ "샴": 727,
732
+ "샵": 728,
733
+ "샹": 729,
734
+ "서": 730,
735
+ "석": 731,
736
+ "섞": 732,
737
+ "선": 733,
738
+ "설": 734,
739
+ "섬": 735,
740
+ "섭": 736,
741
+ "섯": 737,
742
+ "성": 738,
743
+ "세": 739,
744
+ "센": 740,
745
+ "셀": 741,
746
+ "셉": 742,
747
+ "셋": 743,
748
+ "셌": 744,
749
+ "셔": 745,
750
+ "션": 746,
751
+ "셜": 747,
752
+ "셨": 748,
753
+ "셩": 749,
754
+ "셰": 750,
755
+ "소": 751,
756
+ "속": 752,
757
+ "손": 753,
758
+ "솔": 754,
759
+ "솜": 755,
760
+ "솟": 756,
761
+ "송": 757,
762
+ "솥": 758,
763
+ "솩": 759,
764
+ "쇠": 760,
765
+ "쇼": 761,
766
+ "숏": 762,
767
+ "숑": 763,
768
+ "수": 764,
769
+ "숙": 765,
770
+ "순": 766,
771
+ "숟": 767,
772
+ "술": 768,
773
+ "숨": 769,
774
+ "숩": 770,
775
+ "숫": 771,
776
+ "숭": 772,
777
+ "숯": 773,
778
+ "숱": 774,
779
+ "숲": 775,
780
+ "쉬": 776,
781
+ "쉭": 777,
782
+ "쉰": 778,
783
+ "쉴": 779,
784
+ "쉼": 780,
785
+ "쉽": 781,
786
+ "슈": 782,
787
+ "슉": 783,
788
+ "슘": 784,
789
+ "슝": 785,
790
+ "스": 786,
791
+ "슥": 787,
792
+ "슨": 788,
793
+ "슬": 789,
794
+ "슴": 790,
795
+ "습": 791,
796
+ "슷": 792,
797
+ "승": 793,
798
+ "시": 794,
799
+ "식": 795,
800
+ "신": 796,
801
+ "싣": 797,
802
+ "실": 798,
803
+ "싫": 799,
804
+ "심": 800,
805
+ "십": 801,
806
+ "싱": 802,
807
+ "싶": 803,
808
+ "싸": 804,
809
+ "싹": 805,
810
+ "싼": 806,
811
+ "쌀": 807,
812
+ "쌈": 808,
813
+ "쌉": 809,
814
+ "쌌": 810,
815
+ "쌍": 811,
816
+ "쌓": 812,
817
+ "쌔": 813,
818
+ "쌩": 814,
819
+ "쌰": 815,
820
+ "써": 816,
821
+ "썩": 817,
822
+ "썬": 818,
823
+ "썰": 819,
824
+ "썹": 820,
825
+ "썼": 821,
826
+ "썽": 822,
827
+ "쎄": 823,
828
+ "쎈": 824,
829
+ "쏘": 825,
830
+ "쏙": 826,
831
+ "쏜": 827,
832
+ "쏟": 828,
833
+ "쏠": 829,
834
+ "쏩": 830,
835
+ "쏭": 831,
836
+ "쏴": 832,
837
+ "쏵": 833,
838
+ "쐬": 834,
839
+ "쐴": 835,
840
+ "쑝": 836,
841
+ "쑤": 837,
842
+ "쑥": 838,
843
+ "쒜": 839,
844
+ "쓕": 840,
845
+ "쓰": 841,
846
+ "쓱": 842,
847
+ "쓴": 843,
848
+ "쓸": 844,
849
+ "씀": 845,
850
+ "씁": 846,
851
+ "씌": 847,
852
+ "씨": 848,
853
+ "씩": 849,
854
+ "씬": 850,
855
+ "씸": 851,
856
+ "씹": 852,
857
+ "씻": 853,
858
+ "아": 854,
859
+ "악": 855,
860
+ "앆": 856,
861
+ "안": 857,
862
+ "앉": 858,
863
+ "않": 859,
864
+ "알": 860,
865
+ "암": 861,
866
+ "압": 862,
867
+ "앗": 863,
868
+ "았": 864,
869
+ "앙": 865,
870
+ "앞": 866,
871
+ "애": 867,
872
+ "액": 868,
873
+ "앤": 869,
874
+ "앨": 870,
875
+ "앰": 871,
876
+ "앱": 872,
877
+ "앴": 873,
878
+ "앵": 874,
879
+ "야": 875,
880
+ "약": 876,
881
+ "얀": 877,
882
+ "얄": 878,
883
+ "얇": 879,
884
+ "얌": 880,
885
+ "얍": 881,
886
+ "양": 882,
887
+ "얓": 883,
888
+ "얗": 884,
889
+ "얘": 885,
890
+ "얜": 886,
891
+ "어": 887,
892
+ "억": 888,
893
+ "언": 889,
894
+ "얹": 890,
895
+ "얻": 891,
896
+ "얼": 892,
897
+ "엄": 893,
898
+ "업": 894,
899
+ "없": 895,
900
+ "엇": 896,
901
+ "었": 897,
902
+ "엉": 898,
903
+ "엊": 899,
904
+ "엌": 900,
905
+ "에": 901,
906
+ "엑": 902,
907
+ "엔": 903,
908
+ "엘": 904,
909
+ "엠": 905,
910
+ "여": 906,
911
+ "역": 907,
912
+ "엮": 908,
913
+ "연": 909,
914
+ "열": 910,
915
+ "염": 911,
916
+ "엽": 912,
917
+ "엿": 913,
918
+ "였": 914,
919
+ "영": 915,
920
+ "옆": 916,
921
+ "옇": 917,
922
+ "예": 918,
923
+ "옛": 919,
924
+ "오": 920,
925
+ "옥": 921,
926
+ "온": 922,
927
+ "올": 923,
928
+ "옮": 924,
929
+ "옳": 925,
930
+ "옴": 926,
931
+ "옵": 927,
932
+ "옷": 928,
933
+ "옹": 929,
934
+ "와": 930,
935
+ "완": 931,
936
+ "왔": 932,
937
+ "왕": 933,
938
+ "왜": 934,
939
+ "왠": 935,
940
+ "외": 936,
941
+ "왼": 937,
942
+ "요": 938,
943
+ "욕": 939,
944
+ "욜": 940,
945
+ "용": 941,
946
+ "우": 942,
947
+ "욱": 943,
948
+ "운": 944,
949
+ "울": 945,
950
+ "움": 946,
951
+ "웁": 947,
952
+ "웃": 948,
953
+ "웅": 949,
954
+ "워": 950,
955
+ "원": 951,
956
+ "월": 952,
957
+ "웠": 953,
958
+ "웨": 954,
959
+ "웬": 955,
960
+ "웹": 956,
961
+ "위": 957,
962
+ "윈": 958,
963
+ "윗": 959,
964
+ "윙": 960,
965
+ "유": 961,
966
+ "육": 962,
967
+ "윤": 963,
968
+ "율": 964,
969
+ "융": 965,
970
+ "으": 966,
971
+ "은": 967,
972
+ "을": 968,
973
+ "음": 969,
974
+ "읍": 970,
975
+ "읏": 971,
976
+ "응": 972,
977
+ "읒": 973,
978
+ "의": 974,
979
+ "이": 975,
980
+ "익": 976,
981
+ "인": 977,
982
+ "일": 978,
983
+ "읽": 979,
984
+ "잃": 980,
985
+ "임": 981,
986
+ "입": 982,
987
+ "잇": 983,
988
+ "있": 984,
989
+ "잉": 985,
990
+ "잊": 986,
991
+ "잎": 987,
992
+ "자": 988,
993
+ "작": 989,
994
+ "잔": 990,
995
+ "잖": 991,
996
+ "잘": 992,
997
+ "잠": 993,
998
+ "잡": 994,
999
+ "잤": 995,
1000
+ "장": 996,
1001
+ "잦": 997,
1002
+ "재": 998,
1003
+ "잽": 999,
1004
+ "잿": 1000,
1005
+ "쟁": 1001,
1006
+ "쟈": 1002,
1007
+ "쟤": 1003,
1008
+ "저": 1004,
1009
+ "적": 1005,
1010
+ "전": 1006,
1011
+ "절": 1007,
1012
+ "젊": 1008,
1013
+ "점": 1009,
1014
+ "접": 1010,
1015
+ "젓": 1011,
1016
+ "정": 1012,
1017
+ "젖": 1013,
1018
+ "제": 1014,
1019
+ "젠": 1015,
1020
+ "젤": 1016,
1021
+ "젯": 1017,
1022
+ "져": 1018,
1023
+ "졌": 1019,
1024
+ "조": 1020,
1025
+ "족": 1021,
1026
+ "존": 1022,
1027
+ "졸": 1023,
1028
+ "좀": 1024,
1029
+ "좁": 1025,
1030
+ "종": 1026,
1031
+ "좋": 1027,
1032
+ "좌": 1028,
1033
+ "좔": 1029,
1034
+ "죄": 1030,
1035
+ "죠": 1031,
1036
+ "주": 1032,
1037
+ "죽": 1033,
1038
+ "준": 1034,
1039
+ "줄": 1035,
1040
+ "줌": 1036,
1041
+ "줍": 1037,
1042
+ "중": 1038,
1043
+ "줘": 1039,
1044
+ "줬": 1040,
1045
+ "쥐": 1041,
1046
+ "쥔": 1042,
1047
+ "쥬": 1043,
1048
+ "즈": 1044,
1049
+ "즉": 1045,
1050
+ "즌": 1046,
1051
+ "즐": 1047,
1052
+ "즘": 1048,
1053
+ "즙": 1049,
1054
+ "증": 1050,
1055
+ "지": 1051,
1056
+ "직": 1052,
1057
+ "진": 1053,
1058
+ "질": 1054,
1059
+ "짐": 1055,
1060
+ "집": 1056,
1061
+ "짓": 1057,
1062
+ "징": 1058,
1063
+ "짖": 1059,
1064
+ "짙": 1060,
1065
+ "짚": 1061,
1066
+ "짜": 1062,
1067
+ "짝": 1063,
1068
+ "짠": 1064,
1069
+ "짤": 1065,
1070
+ "짧": 1066,
1071
+ "짬": 1067,
1072
+ "짭": 1068,
1073
+ "짰": 1069,
1074
+ "짱": 1070,
1075
+ "째": 1071,
1076
+ "쨋": 1072,
1077
+ "쨌": 1073,
1078
+ "쨍": 1074,
1079
+ "쨰": 1075,
1080
+ "쩄": 1076,
1081
+ "쩌": 1077,
1082
+ "쩍": 1078,
1083
+ "쩐": 1079,
1084
+ "쩔": 1080,
1085
+ "쩜": 1081,
1086
+ "쩝": 1082,
1087
+ "쩡": 1083,
1088
+ "쪄": 1084,
1089
+ "쪘": 1085,
1090
+ "쪼": 1086,
1091
+ "쪽": 1087,
1092
+ "쫀": 1088,
1093
+ "쫄": 1089,
1094
+ "쫌": 1090,
1095
+ "쫑": 1091,
1096
+ "쫓": 1092,
1097
+ "쫘": 1093,
1098
+ "쫙": 1094,
1099
+ "쫜": 1095,
1100
+ "쫠": 1096,
1101
+ "쬐": 1097,
1102
+ "쭈": 1098,
1103
+ "쭉": 1099,
1104
+ "쭤": 1100,
1105
+ "쮸": 1101,
1106
+ "쯔": 1102,
1107
+ "쯜": 1103,
1108
+ "쯤": 1104,
1109
+ "쯧": 1105,
1110
+ "찌": 1106,
1111
+ "찍": 1107,
1112
+ "찐": 1108,
1113
+ "찔": 1109,
1114
+ "찜": 1110,
1115
+ "찝": 1111,
1116
+ "찡": 1112,
1117
+ "찢": 1113,
1118
+ "차": 1114,
1119
+ "착": 1115,
1120
+ "찬": 1116,
1121
+ "찮": 1117,
1122
+ "찰": 1118,
1123
+ "참": 1119,
1124
+ "찹": 1120,
1125
+ "찼": 1121,
1126
+ "창": 1122,
1127
+ "찾": 1123,
1128
+ "채": 1124,
1129
+ "책": 1125,
1130
+ "챔": 1126,
1131
+ "챕": 1127,
1132
+ "챙": 1128,
1133
+ "처": 1129,
1134
+ "척": 1130,
1135
+ "천": 1131,
1136
+ "철": 1132,
1137
+ "첨": 1133,
1138
+ "첩": 1134,
1139
+ "첫": 1135,
1140
+ "청": 1136,
1141
+ "체": 1137,
1142
+ "첸": 1138,
1143
+ "쳐": 1139,
1144
+ "쳤": 1140,
1145
+ "초": 1141,
1146
+ "촉": 1142,
1147
+ "촌": 1143,
1148
+ "촘": 1144,
1149
+ "총": 1145,
1150
+ "촤": 1146,
1151
+ "촥": 1147,
1152
+ "촬": 1148,
1153
+ "최": 1149,
1154
+ "쵸": 1150,
1155
+ "추": 1151,
1156
+ "축": 1152,
1157
+ "춘": 1153,
1158
+ "출": 1154,
1159
+ "춤": 1155,
1160
+ "춥": 1156,
1161
+ "춧": 1157,
1162
+ "충": 1158,
1163
+ "춰": 1159,
1164
+ "췄": 1160,
1165
+ "취": 1161,
1166
+ "츄": 1162,
1167
+ "츠": 1163,
1168
+ "측": 1164,
1169
+ "츨": 1165,
1170
+ "층": 1166,
1171
+ "치": 1167,
1172
+ "칙": 1168,
1173
+ "친": 1169,
1174
+ "칠": 1170,
1175
+ "침": 1171,
1176
+ "칩": 1172,
1177
+ "칫": 1173,
1178
+ "칭": 1174,
1179
+ "카": 1175,
1180
+ "칸": 1176,
1181
+ "칼": 1177,
1182
+ "캄": 1178,
1183
+ "캉": 1179,
1184
+ "캐": 1180,
1185
+ "캑": 1181,
1186
+ "캘": 1182,
1187
+ "캠": 1183,
1188
+ "캡": 1184,
1189
+ "캬": 1185,
1190
+ "커": 1186,
1191
+ "컨": 1187,
1192
+ "컬": 1188,
1193
+ "컴": 1189,
1194
+ "컵": 1190,
1195
+ "컷": 1191,
1196
+ "컸": 1192,
1197
+ "컹": 1193,
1198
+ "케": 1194,
1199
+ "켓": 1195,
1200
+ "켜": 1196,
1201
+ "켠": 1197,
1202
+ "켤": 1198,
1203
+ "켰": 1199,
1204
+ "코": 1200,
1205
+ "콕": 1201,
1206
+ "콘": 1202,
1207
+ "콜": 1203,
1208
+ "콤": 1204,
1209
+ "콧": 1205,
1210
+ "콩": 1206,
1211
+ "콱": 1207,
1212
+ "쾅": 1208,
1213
+ "쾌": 1209,
1214
+ "쿠": 1210,
1215
+ "쿡": 1211,
1216
+ "쿨": 1212,
1217
+ "쿰": 1213,
1218
+ "쿱": 1214,
1219
+ "쿵": 1215,
1220
+ "퀄": 1216,
1221
+ "퀴": 1217,
1222
+ "퀸": 1218,
1223
+ "큐": 1219,
1224
+ "크": 1220,
1225
+ "큰": 1221,
1226
+ "클": 1222,
1227
+ "큼": 1223,
1228
+ "큽": 1224,
1229
+ "키": 1225,
1230
+ "킨": 1226,
1231
+ "킬": 1227,
1232
+ "킴": 1228,
1233
+ "킵": 1229,
1234
+ "킷": 1230,
1235
+ "킹": 1231,
1236
+ "타": 1232,
1237
+ "탁": 1233,
1238
+ "탄": 1234,
1239
+ "탈": 1235,
1240
+ "탐": 1236,
1241
+ "탑": 1237,
1242
+ "탓": 1238,
1243
+ "탔": 1239,
1244
+ "탕": 1240,
1245
+ "태": 1241,
1246
+ "택": 1242,
1247
+ "탠": 1243,
1248
+ "탭": 1244,
1249
+ "탱": 1245,
1250
+ "터": 1246,
1251
+ "턱": 1247,
1252
+ "턴": 1248,
1253
+ "털": 1249,
1254
+ "텀": 1250,
1255
+ "텁": 1251,
1256
+ "텃": 1252,
1257
+ "텅": 1253,
1258
+ "테": 1254,
1259
+ "텍": 1255,
1260
+ "텐": 1256,
1261
+ "텔": 1257,
1262
+ "템": 1258,
1263
+ "텝": 1259,
1264
+ "텨": 1260,
1265
+ "텼": 1261,
1266
+ "토": 1262,
1267
+ "톡": 1263,
1268
+ "톤": 1264,
1269
+ "톨": 1265,
1270
+ "톰": 1266,
1271
+ "톱": 1267,
1272
+ "통": 1268,
1273
+ "퇴": 1269,
1274
+ "투": 1270,
1275
+ "툭": 1271,
1276
+ "툴": 1272,
1277
+ "툼": 1273,
1278
+ "퉁": 1274,
1279
+ "퉜": 1275,
1280
+ "튀": 1276,
1281
+ "튄": 1277,
1282
+ "튈": 1278,
1283
+ "튜": 1279,
1284
+ "트": 1280,
1285
+ "특": 1281,
1286
+ "튼": 1282,
1287
+ "틀": 1283,
1288
+ "틈": 1284,
1289
+ "티": 1285,
1290
+ "틱": 1286,
1291
+ "틴": 1287,
1292
+ "틸": 1288,
1293
+ "팀": 1289,
1294
+ "팁": 1290,
1295
+ "팅": 1291,
1296
+ "파": 1292,
1297
+ "팍": 1293,
1298
+ "팎": 1294,
1299
+ "판": 1295,
1300
+ "팔": 1296,
1301
+ "팝": 1297,
1302
+ "팟": 1298,
1303
+ "팠": 1299,
1304
+ "팡": 1300,
1305
+ "팥": 1301,
1306
+ "패": 1302,
1307
+ "팩": 1303,
1308
+ "팬": 1304,
1309
+ "팸": 1305,
1310
+ "팽": 1306,
1311
+ "퍄": 1307,
1312
+ "퍼": 1308,
1313
+ "퍽": 1309,
1314
+ "펀": 1310,
1315
+ "펄": 1311,
1316
+ "펌": 1312,
1317
+ "펐": 1313,
1318
+ "페": 1314,
1319
+ "펙": 1315,
1320
+ "펜": 1316,
1321
+ "펩": 1317,
1322
+ "펴": 1318,
1323
+ "편": 1319,
1324
+ "펼": 1320,
1325
+ "폈": 1321,
1326
+ "평": 1322,
1327
+ "폐": 1323,
1328
+ "포": 1324,
1329
+ "폭": 1325,
1330
+ "폰": 1326,
1331
+ "폴": 1327,
1332
+ "폼": 1328,
1333
+ "퐁": 1329,
1334
+ "표": 1330,
1335
+ "푸": 1331,
1336
+ "푹": 1332,
1337
+ "푼": 1333,
1338
+ "풀": 1334,
1339
+ "품": 1335,
1340
+ "풉": 1336,
1341
+ "풋": 1337,
1342
+ "풍": 1338,
1343
+ "퓨": 1339,
1344
+ "프": 1340,
1345
+ "픈": 1341,
1346
+ "플": 1342,
1347
+ "픔": 1343,
1348
+ "픕": 1344,
1349
+ "피": 1345,
1350
+ "픽": 1346,
1351
+ "핀": 1347,
1352
+ "필": 1348,
1353
+ "핏": 1349,
1354
+ "핑": 1350,
1355
+ "하": 1351,
1356
+ "학": 1352,
1357
+ "한": 1353,
1358
+ "할": 1354,
1359
+ "함": 1355,
1360
+ "합": 1356,
1361
+ "핫": 1357,
1362
+ "항": 1358,
1363
+ "해": 1359,
1364
+ "핵": 1360,
1365
+ "핸": 1361,
1366
+ "햄": 1362,
1367
+ "햅": 1363,
1368
+ "햇": 1364,
1369
+ "했": 1365,
1370
+ "행": 1366,
1371
+ "햐": 1367,
1372
+ "향": 1368,
1373
+ "허": 1369,
1374
+ "헉": 1370,
1375
+ "헐": 1371,
1376
+ "험": 1372,
1377
+ "헛": 1373,
1378
+ "헤": 1374,
1379
+ "헥": 1375,
1380
+ "헨": 1376,
1381
+ "헬": 1377,
1382
+ "헷": 1378,
1383
+ "헹": 1379,
1384
+ "혀": 1380,
1385
+ "혁": 1381,
1386
+ "현": 1382,
1387
+ "혈": 1383,
1388
+ "협": 1384,
1389
+ "혓": 1385,
1390
+ "혔": 1386,
1391
+ "형": 1387,
1392
+ "혜": 1388,
1393
+ "호": 1389,
1394
+ "혹": 1390,
1395
+ "혼": 1391,
1396
+ "홀": 1392,
1397
+ "홈": 1393,
1398
+ "홉": 1394,
1399
+ "홍": 1395,
1400
+ "화": 1396,
1401
+ "확": 1397,
1402
+ "환": 1398,
1403
+ "활": 1399,
1404
+ "황": 1400,
1405
+ "회": 1401,
1406
+ "획": 1402,
1407
+ "횐": 1403,
1408
+ "횟": 1404,
1409
+ "효": 1405,
1410
+ "횩": 1406,
1411
+ "후": 1407,
1412
+ "훅": 1408,
1413
+ "훈": 1409,
1414
+ "훌": 1410,
1415
+ "훔": 1411,
1416
+ "훨": 1412,
1417
+ "휑": 1413,
1418
+ "휘": 1414,
1419
+ "휴": 1415,
1420
+ "흉": 1416,
1421
+ "흐": 1417,
1422
+ "흑": 1418,
1423
+ "흔": 1419,
1424
+ "흘": 1420,
1425
+ "흙": 1421,
1426
+ "흠": 1422,
1427
+ "흡": 1423,
1428
+ "흣": 1424,
1429
+ "흥": 1425,
1430
+ "흩": 1426,
1431
+ "희": 1427,
1432
+ "흰": 1428,
1433
+ "히": 1429,
1434
+ "힌": 1430,
1435
+ "힐": 1431,
1436
+ "힘": 1432,
1437
+ "힙": 1433,
1438
+ "힝": 1434
1439
+ }
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.05,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.05,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 1436,
90
+ "proj_codevector_dim": 768,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.34.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 1439,
116
+ "xvector_output_dim": 512
117
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 39.95,
3
+ "eval_cer": 0.10764723995306297,
4
+ "eval_loss": 0.5172480344772339,
5
+ "eval_runtime": 199.9485,
6
+ "eval_samples": 4606,
7
+ "eval_samples_per_second": 23.036,
8
+ "eval_steps_per_second": 2.881
9
+ }
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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369e1a1e910ba67c97196d52498d998444456ae1d71df877a5481640a7265067
3
+ size 1267801773
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "</s>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "pad_token": "[PAD]",
9
+ "unk_token": "[UNK]"
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1435": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1436": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "1437": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "1438": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [
37
+ "<s>",
38
+ "</s>"
39
+ ],
40
+ "bos_token": "<s>",
41
+ "clean_up_tokenization_spaces": true,
42
+ "config": null,
43
+ "do_lower_case": false,
44
+ "eos_token": "</s>",
45
+ "model_max_length": 1000000000000000019884624838656,
46
+ "pad_token": "[PAD]",
47
+ "processor_class": "Wav2Vec2Processor",
48
+ "replace_word_delimiter_char": " ",
49
+ "target_lang": null,
50
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
51
+ "tokenizer_file": null,
52
+ "tokenizer_type": "wav2vec2",
53
+ "trust_remote_code": false,
54
+ "unk_token": "[UNK]",
55
+ "word_delimiter_token": "|"
56
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 39.95,
3
+ "train_loss": 0.7889066434568829,
4
+ "train_runtime": 39248.6958,
5
+ "train_samples": 36905,
6
+ "train_samples_per_second": 37.611,
7
+ "train_steps_per_second": 0.587
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 39.9479843953186,
5
+ "eval_steps": 1500,
6
+ "global_step": 23040,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.6,
13
+ "learning_rate": 0.0002932622504537205,
14
+ "loss": 6.742,
15
+ "step": 1500
16
+ },
17
+ {
18
+ "epoch": 2.6,
19
+ "eval_cer": 0.2330206972312148,
20
+ "eval_loss": 0.9037942886352539,
21
+ "eval_runtime": 202.8675,
22
+ "eval_samples_per_second": 22.704,
23
+ "eval_steps_per_second": 2.839,
24
+ "step": 1500
25
+ },
26
+ {
27
+ "epoch": 5.2,
28
+ "learning_rate": 0.00027284482758620687,
29
+ "loss": 0.9228,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 5.2,
34
+ "eval_cer": 0.1655612053827781,
35
+ "eval_loss": 0.6193090677261353,
36
+ "eval_runtime": 202.6276,
37
+ "eval_samples_per_second": 22.731,
38
+ "eval_steps_per_second": 2.843,
39
+ "step": 3000
40
+ },
41
+ {
42
+ "epoch": 7.8,
43
+ "learning_rate": 0.00025242740471869324,
44
+ "loss": 0.6805,
45
+ "step": 4500
46
+ },
47
+ {
48
+ "epoch": 7.8,
49
+ "eval_cer": 0.14813458609698654,
50
+ "eval_loss": 0.5522382259368896,
51
+ "eval_runtime": 201.9891,
52
+ "eval_samples_per_second": 22.803,
53
+ "eval_steps_per_second": 2.852,
54
+ "step": 4500
55
+ },
56
+ {
57
+ "epoch": 10.4,
58
+ "learning_rate": 0.00023200998185117966,
59
+ "loss": 0.5577,
60
+ "step": 6000
61
+ },
62
+ {
63
+ "epoch": 10.4,
64
+ "eval_cer": 0.1348940171935986,
65
+ "eval_loss": 0.5135979652404785,
66
+ "eval_runtime": 208.2736,
67
+ "eval_samples_per_second": 22.115,
68
+ "eval_steps_per_second": 2.766,
69
+ "step": 6000
70
+ },
71
+ {
72
+ "epoch": 13.0,
73
+ "learning_rate": 0.00021160617059891106,
74
+ "loss": 0.4797,
75
+ "step": 7500
76
+ },
77
+ {
78
+ "epoch": 13.0,
79
+ "eval_cer": 0.1312322633799652,
80
+ "eval_loss": 0.5074160099029541,
81
+ "eval_runtime": 207.3615,
82
+ "eval_samples_per_second": 22.212,
83
+ "eval_steps_per_second": 2.778,
84
+ "step": 7500
85
+ },
86
+ {
87
+ "epoch": 15.6,
88
+ "learning_rate": 0.00019120235934664247,
89
+ "loss": 0.4161,
90
+ "step": 9000
91
+ },
92
+ {
93
+ "epoch": 15.6,
94
+ "eval_cer": 0.12432486414061135,
95
+ "eval_loss": 0.4958959221839905,
96
+ "eval_runtime": 198.4858,
97
+ "eval_samples_per_second": 23.206,
98
+ "eval_steps_per_second": 2.902,
99
+ "step": 9000
100
+ },
101
+ {
102
+ "epoch": 18.21,
103
+ "learning_rate": 0.00017078493647912883,
104
+ "loss": 0.3701,
105
+ "step": 10500
106
+ },
107
+ {
108
+ "epoch": 18.21,
109
+ "eval_cer": 0.12240244338845382,
110
+ "eval_loss": 0.4947836697101593,
111
+ "eval_runtime": 198.4077,
112
+ "eval_samples_per_second": 23.215,
113
+ "eval_steps_per_second": 2.903,
114
+ "step": 10500
115
+ },
116
+ {
117
+ "epoch": 20.81,
118
+ "learning_rate": 0.00015038112522686024,
119
+ "loss": 0.3307,
120
+ "step": 12000
121
+ },
122
+ {
123
+ "epoch": 20.81,
124
+ "eval_cer": 0.11993908173200955,
125
+ "eval_loss": 0.48810431361198425,
126
+ "eval_runtime": 197.2477,
127
+ "eval_samples_per_second": 23.351,
128
+ "eval_steps_per_second": 2.92,
129
+ "step": 12000
130
+ },
131
+ {
132
+ "epoch": 23.41,
133
+ "learning_rate": 0.00012996370235934663,
134
+ "loss": 0.2946,
135
+ "step": 13500
136
+ },
137
+ {
138
+ "epoch": 23.41,
139
+ "eval_cer": 0.1179251171345112,
140
+ "eval_loss": 0.4970262050628662,
141
+ "eval_runtime": 201.6098,
142
+ "eval_samples_per_second": 22.846,
143
+ "eval_steps_per_second": 2.857,
144
+ "step": 13500
145
+ },
146
+ {
147
+ "epoch": 26.01,
148
+ "learning_rate": 0.00010954627949183302,
149
+ "loss": 0.2636,
150
+ "step": 15000
151
+ },
152
+ {
153
+ "epoch": 26.01,
154
+ "eval_cer": 0.11448806185035078,
155
+ "eval_loss": 0.4949529767036438,
156
+ "eval_runtime": 204.2568,
157
+ "eval_samples_per_second": 22.55,
158
+ "eval_steps_per_second": 2.82,
159
+ "step": 15000
160
+ },
161
+ {
162
+ "epoch": 28.61,
163
+ "learning_rate": 8.915607985480944e-05,
164
+ "loss": 0.2367,
165
+ "step": 16500
166
+ },
167
+ {
168
+ "epoch": 28.61,
169
+ "eval_cer": 0.11192483418080741,
170
+ "eval_loss": 0.49051955342292786,
171
+ "eval_runtime": 200.659,
172
+ "eval_samples_per_second": 22.954,
173
+ "eval_steps_per_second": 2.871,
174
+ "step": 16500
175
+ },
176
+ {
177
+ "epoch": 31.21,
178
+ "learning_rate": 6.875226860254083e-05,
179
+ "loss": 0.2157,
180
+ "step": 18000
181
+ },
182
+ {
183
+ "epoch": 31.21,
184
+ "eval_cer": 0.11102604006291558,
185
+ "eval_loss": 0.5065664649009705,
186
+ "eval_runtime": 198.3314,
187
+ "eval_samples_per_second": 23.224,
188
+ "eval_steps_per_second": 2.904,
189
+ "step": 18000
190
+ },
191
+ {
192
+ "epoch": 33.81,
193
+ "learning_rate": 4.833484573502722e-05,
194
+ "loss": 0.1979,
195
+ "step": 19500
196
+ },
197
+ {
198
+ "epoch": 33.81,
199
+ "eval_cer": 0.11034362230673846,
200
+ "eval_loss": 0.5133121609687805,
201
+ "eval_runtime": 198.0306,
202
+ "eval_samples_per_second": 23.259,
203
+ "eval_steps_per_second": 2.909,
204
+ "step": 19500
205
+ },
206
+ {
207
+ "epoch": 36.41,
208
+ "learning_rate": 2.791742286751361e-05,
209
+ "loss": 0.1808,
210
+ "step": 21000
211
+ },
212
+ {
213
+ "epoch": 36.41,
214
+ "eval_cer": 0.10908697497524156,
215
+ "eval_loss": 0.516022801399231,
216
+ "eval_runtime": 198.8874,
217
+ "eval_samples_per_second": 23.159,
218
+ "eval_steps_per_second": 2.896,
219
+ "step": 21000
220
+ },
221
+ {
222
+ "epoch": 39.01,
223
+ "learning_rate": 7.527223230490017e-06,
224
+ "loss": 0.17,
225
+ "step": 22500
226
+ },
227
+ {
228
+ "epoch": 39.01,
229
+ "eval_cer": 0.10736428624928221,
230
+ "eval_loss": 0.5128792524337769,
231
+ "eval_runtime": 200.4673,
232
+ "eval_samples_per_second": 22.976,
233
+ "eval_steps_per_second": 2.873,
234
+ "step": 22500
235
+ },
236
+ {
237
+ "epoch": 39.95,
238
+ "step": 23040,
239
+ "total_flos": 1.6932808921238733e+20,
240
+ "train_loss": 0.7889066434568829,
241
+ "train_runtime": 39248.6958,
242
+ "train_samples_per_second": 37.611,
243
+ "train_steps_per_second": 0.587
244
+ }
245
+ ],
246
+ "logging_steps": 1500,
247
+ "max_steps": 23040,
248
+ "num_train_epochs": 40,
249
+ "save_steps": 1500,
250
+ "total_flos": 1.6932808921238733e+20,
251
+ "trial_name": null,
252
+ "trial_params": null
253
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84fd5eecba213b71cf981134653cb7eabfffd55d4675b8e4237fa1cee57c8e6
3
+ size 4027
vocab.json ADDED
@@ -0,0 +1,1439 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 1,
3
+ "0": 2,
4
+ "1": 3,
5
+ "2": 4,
6
+ "3": 5,
7
+ "4": 6,
8
+ "5": 7,
9
+ "6": 8,
10
+ "7": 9,
11
+ "8": 10,
12
+ "9": 11,
13
+ "[PAD]": 1436,
14
+ "[UNK]": 1435,
15
+ "a": 12,
16
+ "b": 13,
17
+ "c": 14,
18
+ "d": 15,
19
+ "e": 16,
20
+ "f": 17,
21
+ "g": 18,
22
+ "h": 19,
23
+ "i": 20,
24
+ "j": 21,
25
+ "k": 22,
26
+ "l": 23,
27
+ "m": 24,
28
+ "n": 25,
29
+ "o": 26,
30
+ "p": 27,
31
+ "q": 28,
32
+ "r": 29,
33
+ "s": 30,
34
+ "t": 31,
35
+ "u": 32,
36
+ "v": 33,
37
+ "w": 34,
38
+ "x": 35,
39
+ "y": 36,
40
+ "z": 37,
41
+ "|": 0,
42
+ "}": 38,
43
+ "ㅋ": 39,
44
+ "ㅡ": 40,
45
+ "가": 41,
46
+ "각": 42,
47
+ "간": 43,
48
+ "갇": 44,
49
+ "갈": 45,
50
+ "감": 46,
51
+ "갑": 47,
52
+ "값": 48,
53
+ "갓": 49,
54
+ "갔": 50,
55
+ "강": 51,
56
+ "갖": 52,
57
+ "같": 53,
58
+ "갛": 54,
59
+ "개": 55,
60
+ "객": 56,
61
+ "갠": 57,
62
+ "갤": 58,
63
+ "갬": 59,
64
+ "갭": 60,
65
+ "갯": 61,
66
+ "갰": 62,
67
+ "갱": 63,
68
+ "걀": 64,
69
+ "걍": 65,
70
+ "걔": 66,
71
+ "걘": 67,
72
+ "거": 68,
73
+ "걱": 69,
74
+ "건": 70,
75
+ "걷": 71,
76
+ "걸": 72,
77
+ "검": 73,
78
+ "겁": 74,
79
+ "것": 75,
80
+ "겅": 76,
81
+ "겉": 77,
82
+ "겋": 78,
83
+ "게": 79,
84
+ "겐": 80,
85
+ "겔": 81,
86
+ "겟": 82,
87
+ "겠": 83,
88
+ "겨": 84,
89
+ "격": 85,
90
+ "겪": 86,
91
+ "견": 87,
92
+ "결": 88,
93
+ "겸": 89,
94
+ "겹": 90,
95
+ "겼": 91,
96
+ "경": 92,
97
+ "곁": 93,
98
+ "계": 94,
99
+ "고": 95,
100
+ "곡": 96,
101
+ "곤": 97,
102
+ "곧": 98,
103
+ "골": 99,
104
+ "곰": 100,
105
+ "곱": 101,
106
+ "곳": 102,
107
+ "공": 103,
108
+ "곶": 104,
109
+ "과": 105,
110
+ "관": 106,
111
+ "괄": 107,
112
+ "괍": 108,
113
+ "광": 109,
114
+ "괘": 110,
115
+ "괜": 111,
116
+ "괞": 112,
117
+ "괴": 113,
118
+ "굉": 114,
119
+ "교": 115,
120
+ "굔": 116,
121
+ "구": 117,
122
+ "국": 118,
123
+ "군": 119,
124
+ "굳": 120,
125
+ "굴": 121,
126
+ "굵": 122,
127
+ "굶": 123,
128
+ "굽": 124,
129
+ "굿": 125,
130
+ "궁": 126,
131
+ "궈": 127,
132
+ "권": 128,
133
+ "궜": 129,
134
+ "귀": 130,
135
+ "귓": 131,
136
+ "규": 132,
137
+ "균": 133,
138
+ "귤": 134,
139
+ "그": 135,
140
+ "극": 136,
141
+ "근": 137,
142
+ "글": 138,
143
+ "긁": 139,
144
+ "금": 140,
145
+ "급": 141,
146
+ "긋": 142,
147
+ "긍": 143,
148
+ "기": 144,
149
+ "긴": 145,
150
+ "길": 146,
151
+ "김": 147,
152
+ "깁": 148,
153
+ "깃": 149,
154
+ "깉": 150,
155
+ "깊": 151,
156
+ "까": 152,
157
+ "깐": 153,
158
+ "깔": 154,
159
+ "깜": 155,
160
+ "깝": 156,
161
+ "깠": 157,
162
+ "깡": 158,
163
+ "깥": 159,
164
+ "깨": 160,
165
+ "깬": 161,
166
+ "깻": 162,
167
+ "깼": 163,
168
+ "꺼": 164,
169
+ "꺽": 165,
170
+ "껀": 166,
171
+ "껄": 167,
172
+ "껌": 168,
173
+ "껍": 169,
174
+ "껏": 170,
175
+ "껐": 171,
176
+ "껑": 172,
177
+ "께": 173,
178
+ "껴": 174,
179
+ "꼈": 175,
180
+ "꼐": 176,
181
+ "꼬": 177,
182
+ "꼭": 178,
183
+ "꼴": 179,
184
+ "꼼": 180,
185
+ "꼽": 181,
186
+ "꽁": 182,
187
+ "꽂": 183,
188
+ "꽃": 184,
189
+ "꽉": 185,
190
+ "꽝": 186,
191
+ "꽤": 187,
192
+ "꾸": 188,
193
+ "꾹": 189,
194
+ "꾼": 190,
195
+ "꿀": 191,
196
+ "꿈": 192,
197
+ "꿉": 193,
198
+ "꿍": 194,
199
+ "꿔": 195,
200
+ "꿨": 196,
201
+ "뀌": 197,
202
+ "뀐": 198,
203
+ "뀔": 199,
204
+ "뀝": 200,
205
+ "끄": 201,
206
+ "끈": 202,
207
+ "끊": 203,
208
+ "끌": 204,
209
+ "끓": 205,
210
+ "끔": 206,
211
+ "끗": 207,
212
+ "끝": 208,
213
+ "끼": 209,
214
+ "끽": 210,
215
+ "낀": 211,
216
+ "낄": 212,
217
+ "낌": 213,
218
+ "낍": 214,
219
+ "낑": 215,
220
+ "나": 216,
221
+ "낙": 217,
222
+ "낚": 218,
223
+ "난": 219,
224
+ "날": 220,
225
+ "낡": 221,
226
+ "남": 222,
227
+ "납": 223,
228
+ "낫": 224,
229
+ "났": 225,
230
+ "낭": 226,
231
+ "낮": 227,
232
+ "낯": 228,
233
+ "낱": 229,
234
+ "낳": 230,
235
+ "내": 231,
236
+ "낵": 232,
237
+ "낸": 233,
238
+ "낼": 234,
239
+ "냄": 235,
240
+ "냅": 236,
241
+ "냇": 237,
242
+ "냈": 238,
243
+ "냉": 239,
244
+ "냐": 240,
245
+ "냠": 241,
246
+ "냥": 242,
247
+ "너": 243,
248
+ "넉": 244,
249
+ "넌": 245,
250
+ "널": 246,
251
+ "넓": 247,
252
+ "넘": 248,
253
+ "넙": 249,
254
+ "넛": 250,
255
+ "넣": 251,
256
+ "네": 252,
257
+ "넨": 253,
258
+ "넷": 254,
259
+ "녀": 255,
260
+ "녁": 256,
261
+ "년": 257,
262
+ "념": 258,
263
+ "녔": 259,
264
+ "녕": 260,
265
+ "노": 261,
266
+ "녹": 262,
267
+ "논": 263,
268
+ "놀": 264,
269
+ "놈": 265,
270
+ "농": 266,
271
+ "높": 267,
272
+ "놓": 268,
273
+ "놔": 269,
274
+ "놨": 270,
275
+ "뇌": 271,
276
+ "뇨": 272,
277
+ "누": 273,
278
+ "눅": 274,
279
+ "눈": 275,
280
+ "눌": 276,
281
+ "눔": 277,
282
+ "눠": 278,
283
+ "눴": 279,
284
+ "뉘": 280,
285
+ "뉜": 281,
286
+ "뉩": 282,
287
+ "뉴": 283,
288
+ "느": 284,
289
+ "는": 285,
290
+ "늘": 286,
291
+ "늙": 287,
292
+ "능": 288,
293
+ "늦": 289,
294
+ "늬": 290,
295
+ "니": 291,
296
+ "닉": 292,
297
+ "닌": 293,
298
+ "닐": 294,
299
+ "님": 295,
300
+ "닙": 296,
301
+ "닝": 297,
302
+ "다": 298,
303
+ "닥": 299,
304
+ "닦": 300,
305
+ "단": 301,
306
+ "닫": 302,
307
+ "달": 303,
308
+ "닭": 304,
309
+ "닮": 305,
310
+ "닳": 306,
311
+ "담": 307,
312
+ "답": 308,
313
+ "닷": 309,
314
+ "당": 310,
315
+ "닿": 311,
316
+ "대": 312,
317
+ "댁": 313,
318
+ "댄": 314,
319
+ "댈": 315,
320
+ "댑": 316,
321
+ "댓": 317,
322
+ "댔": 318,
323
+ "댕": 319,
324
+ "댗": 320,
325
+ "댜": 321,
326
+ "더": 322,
327
+ "덕": 323,
328
+ "던": 324,
329
+ "덜": 325,
330
+ "덟": 326,
331
+ "덤": 327,
332
+ "덥": 328,
333
+ "덧": 329,
334
+ "덩": 330,
335
+ "덮": 331,
336
+ "데": 332,
337
+ "델": 333,
338
+ "뎁": 334,
339
+ "뎅": 335,
340
+ "도": 336,
341
+ "독": 337,
342
+ "돈": 338,
343
+ "돋": 339,
344
+ "돌": 340,
345
+ "돕": 341,
346
+ "돗": 342,
347
+ "동": 343,
348
+ "돼": 344,
349
+ "됐": 345,
350
+ "되": 346,
351
+ "된": 347,
352
+ "될": 348,
353
+ "됨": 349,
354
+ "됩": 350,
355
+ "두": 351,
356
+ "둑": 352,
357
+ "둔": 353,
358
+ "둘": 354,
359
+ "둠": 355,
360
+ "둡": 356,
361
+ "둣": 357,
362
+ "둥": 358,
363
+ "둬": 359,
364
+ "뒀": 360,
365
+ "뒤": 361,
366
+ "뒷": 362,
367
+ "듕": 363,
368
+ "드": 364,
369
+ "득": 365,
370
+ "든": 366,
371
+ "듣": 367,
372
+ "들": 368,
373
+ "듦": 369,
374
+ "듬": 370,
375
+ "듭": 371,
376
+ "듯": 372,
377
+ "등": 373,
378
+ "디": 374,
379
+ "딘": 375,
380
+ "딜": 376,
381
+ "딥": 377,
382
+ "딨": 378,
383
+ "딩": 379,
384
+ "딪": 380,
385
+ "따": 381,
386
+ "딱": 382,
387
+ "딴": 383,
388
+ "딸": 384,
389
+ "땀": 385,
390
+ "땄": 386,
391
+ "땅": 387,
392
+ "땋": 388,
393
+ "때": 389,
394
+ "땐": 390,
395
+ "땜": 391,
396
+ "땠": 392,
397
+ "땡": 393,
398
+ "떄": 394,
399
+ "떙": 395,
400
+ "떠": 396,
401
+ "떡": 397,
402
+ "떢": 398,
403
+ "떤": 399,
404
+ "떨": 400,
405
+ "떫": 401,
406
+ "떳": 402,
407
+ "떴": 403,
408
+ "떵": 404,
409
+ "떻": 405,
410
+ "떼": 406,
411
+ "뗄": 407,
412
+ "뗐": 408,
413
+ "또": 409,
414
+ "똑": 410,
415
+ "똠": 411,
416
+ "똥": 412,
417
+ "뚜": 413,
418
+ "뚝": 414,
419
+ "뚤": 415,
420
+ "뚫": 416,
421
+ "뚱": 417,
422
+ "뛰": 418,
423
+ "뛸": 419,
424
+ "뜨": 420,
425
+ "뜩": 421,
426
+ "뜬": 422,
427
+ "뜯": 423,
428
+ "뜰": 424,
429
+ "뜸": 425,
430
+ "뜹": 426,
431
+ "뜻": 427,
432
+ "띄": 428,
433
+ "띈": 429,
434
+ "띠": 430,
435
+ "띡": 431,
436
+ "띵": 432,
437
+ "라": 433,
438
+ "락": 434,
439
+ "란": 435,
440
+ "랄": 436,
441
+ "람": 437,
442
+ "랍": 438,
443
+ "랐": 439,
444
+ "랑": 440,
445
+ "랖": 441,
446
+ "랗": 442,
447
+ "래": 443,
448
+ "랙": 444,
449
+ "랜": 445,
450
+ "랠": 446,
451
+ "램": 447,
452
+ "랩": 448,
453
+ "랫": 449,
454
+ "랬": 450,
455
+ "랭": 451,
456
+ "략": 452,
457
+ "량": 453,
458
+ "러": 454,
459
+ "럭": 455,
460
+ "런": 456,
461
+ "럴": 457,
462
+ "럼": 458,
463
+ "럽": 459,
464
+ "렀": 460,
465
+ "렁": 461,
466
+ "렇": 462,
467
+ "레": 463,
468
+ "렉": 464,
469
+ "렌": 465,
470
+ "렐": 466,
471
+ "렘": 467,
472
+ "려": 468,
473
+ "력": 469,
474
+ "련": 470,
475
+ "렬": 471,
476
+ "렴": 472,
477
+ "렵": 473,
478
+ "렸": 474,
479
+ "령": 475,
480
+ "렿": 476,
481
+ "례": 477,
482
+ "로": 478,
483
+ "록": 479,
484
+ "론": 480,
485
+ "롤": 481,
486
+ "롬": 482,
487
+ "롭": 483,
488
+ "롯": 484,
489
+ "롱": 485,
490
+ "롷": 486,
491
+ "뢰": 487,
492
+ "료": 488,
493
+ "룡": 489,
494
+ "루": 490,
495
+ "룩": 491,
496
+ "룰": 492,
497
+ "룽": 493,
498
+ "뤄": 494,
499
+ "류": 495,
500
+ "륙": 496,
501
+ "률": 497,
502
+ "륨": 498,
503
+ "륭": 499,
504
+ "르": 500,
505
+ "륵": 501,
506
+ "른": 502,
507
+ "를": 503,
508
+ "름": 504,
509
+ "릅": 505,
510
+ "릇": 506,
511
+ "릉": 507,
512
+ "릎": 508,
513
+ "리": 509,
514
+ "릭": 510,
515
+ "린": 511,
516
+ "릴": 512,
517
+ "림": 513,
518
+ "립": 514,
519
+ "릿": 515,
520
+ "링": 516,
521
+ "마": 517,
522
+ "막": 518,
523
+ "만": 519,
524
+ "많": 520,
525
+ "말": 521,
526
+ "맑": 522,
527
+ "맘": 523,
528
+ "맙": 524,
529
+ "맛": 525,
530
+ "망": 526,
531
+ "맞": 527,
532
+ "맡": 528,
533
+ "맣": 529,
534
+ "매": 530,
535
+ "맥": 531,
536
+ "맨": 532,
537
+ "맴": 533,
538
+ "맵": 534,
539
+ "맸": 535,
540
+ "맹": 536,
541
+ "머": 537,
542
+ "먹": 538,
543
+ "먼": 539,
544
+ "멀": 540,
545
+ "멈": 541,
546
+ "멋": 542,
547
+ "멍": 543,
548
+ "메": 544,
549
+ "멕": 545,
550
+ "멘": 546,
551
+ "멜": 547,
552
+ "멤": 548,
553
+ "며": 549,
554
+ "면": 550,
555
+ "멸": 551,
556
+ "명": 552,
557
+ "몇": 553,
558
+ "모": 554,
559
+ "목": 555,
560
+ "몫": 556,
561
+ "몬": 557,
562
+ "몰": 558,
563
+ "몸": 559,
564
+ "몹": 560,
565
+ "못": 561,
566
+ "몽": 562,
567
+ "묘": 563,
568
+ "무": 564,
569
+ "묵": 565,
570
+ "묶": 566,
571
+ "문": 567,
572
+ "묻": 568,
573
+ "물": 569,
574
+ "묽": 570,
575
+ "뭇": 571,
576
+ "뭉": 572,
577
+ "뭐": 573,
578
+ "뭔": 574,
579
+ "뭘": 575,
580
+ "뭡": 576,
581
+ "뮤": 577,
582
+ "므": 578,
583
+ "믄": 579,
584
+ "믈": 580,
585
+ "믐": 581,
586
+ "미": 582,
587
+ "믹": 583,
588
+ "민": 584,
589
+ "믾": 585,
590
+ "믿": 586,
591
+ "밀": 587,
592
+ "밌": 588,
593
+ "밍": 589,
594
+ "및": 590,
595
+ "밑": 591,
596
+ "바": 592,
597
+ "박": 593,
598
+ "밖": 594,
599
+ "반": 595,
600
+ "받": 596,
601
+ "발": 597,
602
+ "밝": 598,
603
+ "밟": 599,
604
+ "밤": 600,
605
+ "밥": 601,
606
+ "밧": 602,
607
+ "방": 603,
608
+ "밭": 604,
609
+ "배": 605,
610
+ "백": 606,
611
+ "밴": 607,
612
+ "밸": 608,
613
+ "뱄": 609,
614
+ "뱅": 610,
615
+ "뱉": 611,
616
+ "버": 612,
617
+ "벅": 613,
618
+ "번": 614,
619
+ "벌": 615,
620
+ "범": 616,
621
+ "법": 617,
622
+ "벗": 618,
623
+ "벚": 619,
624
+ "베": 620,
625
+ "벡": 621,
626
+ "벤": 622,
627
+ "벨": 623,
628
+ "벳": 624,
629
+ "벼": 625,
630
+ "벽": 626,
631
+ "변": 627,
632
+ "별": 628,
633
+ "볍": 629,
634
+ "병": 630,
635
+ "볕": 631,
636
+ "보": 632,
637
+ "복": 633,
638
+ "볶": 634,
639
+ "본": 635,
640
+ "볼": 636,
641
+ "봄": 637,
642
+ "봅": 638,
643
+ "봉": 639,
644
+ "봐": 640,
645
+ "봤": 641,
646
+ "봬": 642,
647
+ "봽": 643,
648
+ "뵀": 644,
649
+ "뵈": 645,
650
+ "뵌": 646,
651
+ "뵐": 647,
652
+ "뵙": 648,
653
+ "뵬": 649,
654
+ "뵹": 650,
655
+ "부": 651,
656
+ "북": 652,
657
+ "분": 653,
658
+ "불": 654,
659
+ "붉": 655,
660
+ "붓": 656,
661
+ "붕": 657,
662
+ "붙": 658,
663
+ "붚": 659,
664
+ "뷔": 660,
665
+ "뷰": 661,
666
+ "브": 662,
667
+ "블": 663,
668
+ "비": 664,
669
+ "빈": 665,
670
+ "빔": 666,
671
+ "빗": 667,
672
+ "빙": 668,
673
+ "빛": 669,
674
+ "빠": 670,
675
+ "빡": 671,
676
+ "빨": 672,
677
+ "빴": 673,
678
+ "빵": 674,
679
+ "빼": 675,
680
+ "뺄": 676,
681
+ "뺏": 677,
682
+ "뺐": 678,
683
+ "뺴": 679,
684
+ "뻐": 680,
685
+ "뻑": 681,
686
+ "뻔": 682,
687
+ "뻗": 683,
688
+ "뻘": 684,
689
+ "뻣": 685,
690
+ "뻥": 686,
691
+ "뼈": 687,
692
+ "뽀": 688,
693
+ "뽁": 689,
694
+ "뽂": 690,
695
+ "���": 691,
696
+ "뽕": 692,
697
+ "뾰": 693,
698
+ "뿅": 694,
699
+ "뿌": 695,
700
+ "뿍": 696,
701
+ "뿐": 697,
702
+ "뿔": 698,
703
+ "뿜": 699,
704
+ "뿝": 700,
705
+ "쁘": 701,
706
+ "쁜": 702,
707
+ "쁠": 703,
708
+ "쁨": 704,
709
+ "쁩": 705,
710
+ "삐": 706,
711
+ "삑": 707,
712
+ "사": 708,
713
+ "삭": 709,
714
+ "산": 710,
715
+ "살": 711,
716
+ "삶": 712,
717
+ "삼": 713,
718
+ "삽": 714,
719
+ "삿": 715,
720
+ "샀": 716,
721
+ "상": 717,
722
+ "새": 718,
723
+ "색": 719,
724
+ "샌": 720,
725
+ "샘": 721,
726
+ "샛": 722,
727
+ "생": 723,
728
+ "샤": 724,
729
+ "샥": 725,
730
+ "샬": 726,
731
+ "샴": 727,
732
+ "샵": 728,
733
+ "샹": 729,
734
+ "서": 730,
735
+ "석": 731,
736
+ "섞": 732,
737
+ "선": 733,
738
+ "설": 734,
739
+ "섬": 735,
740
+ "섭": 736,
741
+ "섯": 737,
742
+ "성": 738,
743
+ "세": 739,
744
+ "센": 740,
745
+ "셀": 741,
746
+ "셉": 742,
747
+ "셋": 743,
748
+ "셌": 744,
749
+ "셔": 745,
750
+ "션": 746,
751
+ "셜": 747,
752
+ "셨": 748,
753
+ "셩": 749,
754
+ "셰": 750,
755
+ "소": 751,
756
+ "속": 752,
757
+ "손": 753,
758
+ "솔": 754,
759
+ "솜": 755,
760
+ "솟": 756,
761
+ "송": 757,
762
+ "솥": 758,
763
+ "솩": 759,
764
+ "쇠": 760,
765
+ "쇼": 761,
766
+ "숏": 762,
767
+ "숑": 763,
768
+ "수": 764,
769
+ "숙": 765,
770
+ "순": 766,
771
+ "숟": 767,
772
+ "술": 768,
773
+ "숨": 769,
774
+ "숩": 770,
775
+ "숫": 771,
776
+ "숭": 772,
777
+ "숯": 773,
778
+ "숱": 774,
779
+ "숲": 775,
780
+ "쉬": 776,
781
+ "쉭": 777,
782
+ "쉰": 778,
783
+ "쉴": 779,
784
+ "쉼": 780,
785
+ "쉽": 781,
786
+ "슈": 782,
787
+ "슉": 783,
788
+ "슘": 784,
789
+ "슝": 785,
790
+ "스": 786,
791
+ "슥": 787,
792
+ "슨": 788,
793
+ "슬": 789,
794
+ "슴": 790,
795
+ "습": 791,
796
+ "슷": 792,
797
+ "승": 793,
798
+ "시": 794,
799
+ "식": 795,
800
+ "신": 796,
801
+ "싣": 797,
802
+ "실": 798,
803
+ "싫": 799,
804
+ "심": 800,
805
+ "십": 801,
806
+ "싱": 802,
807
+ "싶": 803,
808
+ "싸": 804,
809
+ "싹": 805,
810
+ "싼": 806,
811
+ "쌀": 807,
812
+ "쌈": 808,
813
+ "쌉": 809,
814
+ "쌌": 810,
815
+ "쌍": 811,
816
+ "쌓": 812,
817
+ "쌔": 813,
818
+ "쌩": 814,
819
+ "쌰": 815,
820
+ "써": 816,
821
+ "썩": 817,
822
+ "썬": 818,
823
+ "썰": 819,
824
+ "썹": 820,
825
+ "썼": 821,
826
+ "썽": 822,
827
+ "쎄": 823,
828
+ "쎈": 824,
829
+ "쏘": 825,
830
+ "쏙": 826,
831
+ "쏜": 827,
832
+ "쏟": 828,
833
+ "쏠": 829,
834
+ "쏩": 830,
835
+ "쏭": 831,
836
+ "쏴": 832,
837
+ "쏵": 833,
838
+ "쐬": 834,
839
+ "쐴": 835,
840
+ "쑝": 836,
841
+ "쑤": 837,
842
+ "쑥": 838,
843
+ "쒜": 839,
844
+ "쓕": 840,
845
+ "쓰": 841,
846
+ "쓱": 842,
847
+ "쓴": 843,
848
+ "쓸": 844,
849
+ "씀": 845,
850
+ "씁": 846,
851
+ "씌": 847,
852
+ "씨": 848,
853
+ "씩": 849,
854
+ "씬": 850,
855
+ "씸": 851,
856
+ "씹": 852,
857
+ "씻": 853,
858
+ "아": 854,
859
+ "악": 855,
860
+ "앆": 856,
861
+ "안": 857,
862
+ "앉": 858,
863
+ "않": 859,
864
+ "알": 860,
865
+ "암": 861,
866
+ "압": 862,
867
+ "앗": 863,
868
+ "았": 864,
869
+ "앙": 865,
870
+ "앞": 866,
871
+ "애": 867,
872
+ "액": 868,
873
+ "앤": 869,
874
+ "앨": 870,
875
+ "앰": 871,
876
+ "앱": 872,
877
+ "앴": 873,
878
+ "앵": 874,
879
+ "야": 875,
880
+ "약": 876,
881
+ "얀": 877,
882
+ "얄": 878,
883
+ "얇": 879,
884
+ "얌": 880,
885
+ "얍": 881,
886
+ "양": 882,
887
+ "얓": 883,
888
+ "얗": 884,
889
+ "얘": 885,
890
+ "얜": 886,
891
+ "어": 887,
892
+ "억": 888,
893
+ "언": 889,
894
+ "얹": 890,
895
+ "얻": 891,
896
+ "얼": 892,
897
+ "엄": 893,
898
+ "업": 894,
899
+ "없": 895,
900
+ "엇": 896,
901
+ "었": 897,
902
+ "엉": 898,
903
+ "엊": 899,
904
+ "엌": 900,
905
+ "에": 901,
906
+ "엑": 902,
907
+ "엔": 903,
908
+ "엘": 904,
909
+ "엠": 905,
910
+ "여": 906,
911
+ "역": 907,
912
+ "엮": 908,
913
+ "연": 909,
914
+ "열": 910,
915
+ "염": 911,
916
+ "엽": 912,
917
+ "엿": 913,
918
+ "였": 914,
919
+ "영": 915,
920
+ "옆": 916,
921
+ "옇": 917,
922
+ "예": 918,
923
+ "옛": 919,
924
+ "오": 920,
925
+ "옥": 921,
926
+ "온": 922,
927
+ "올": 923,
928
+ "옮": 924,
929
+ "옳": 925,
930
+ "옴": 926,
931
+ "옵": 927,
932
+ "옷": 928,
933
+ "옹": 929,
934
+ "와": 930,
935
+ "완": 931,
936
+ "왔": 932,
937
+ "왕": 933,
938
+ "왜": 934,
939
+ "왠": 935,
940
+ "외": 936,
941
+ "왼": 937,
942
+ "요": 938,
943
+ "욕": 939,
944
+ "욜": 940,
945
+ "용": 941,
946
+ "우": 942,
947
+ "욱": 943,
948
+ "운": 944,
949
+ "울": 945,
950
+ "움": 946,
951
+ "웁": 947,
952
+ "웃": 948,
953
+ "웅": 949,
954
+ "워": 950,
955
+ "원": 951,
956
+ "월": 952,
957
+ "웠": 953,
958
+ "웨": 954,
959
+ "웬": 955,
960
+ "웹": 956,
961
+ "위": 957,
962
+ "윈": 958,
963
+ "윗": 959,
964
+ "윙": 960,
965
+ "유": 961,
966
+ "육": 962,
967
+ "윤": 963,
968
+ "율": 964,
969
+ "융": 965,
970
+ "으": 966,
971
+ "은": 967,
972
+ "을": 968,
973
+ "음": 969,
974
+ "읍": 970,
975
+ "읏": 971,
976
+ "응": 972,
977
+ "읒": 973,
978
+ "의": 974,
979
+ "이": 975,
980
+ "익": 976,
981
+ "인": 977,
982
+ "일": 978,
983
+ "읽": 979,
984
+ "잃": 980,
985
+ "임": 981,
986
+ "입": 982,
987
+ "잇": 983,
988
+ "있": 984,
989
+ "잉": 985,
990
+ "잊": 986,
991
+ "잎": 987,
992
+ "자": 988,
993
+ "작": 989,
994
+ "잔": 990,
995
+ "잖": 991,
996
+ "잘": 992,
997
+ "잠": 993,
998
+ "잡": 994,
999
+ "잤": 995,
1000
+ "장": 996,
1001
+ "잦": 997,
1002
+ "재": 998,
1003
+ "잽": 999,
1004
+ "잿": 1000,
1005
+ "쟁": 1001,
1006
+ "쟈": 1002,
1007
+ "쟤": 1003,
1008
+ "저": 1004,
1009
+ "적": 1005,
1010
+ "전": 1006,
1011
+ "절": 1007,
1012
+ "젊": 1008,
1013
+ "점": 1009,
1014
+ "접": 1010,
1015
+ "젓": 1011,
1016
+ "정": 1012,
1017
+ "젖": 1013,
1018
+ "제": 1014,
1019
+ "젠": 1015,
1020
+ "젤": 1016,
1021
+ "젯": 1017,
1022
+ "져": 1018,
1023
+ "졌": 1019,
1024
+ "조": 1020,
1025
+ "족": 1021,
1026
+ "존": 1022,
1027
+ "졸": 1023,
1028
+ "좀": 1024,
1029
+ "좁": 1025,
1030
+ "종": 1026,
1031
+ "좋": 1027,
1032
+ "좌": 1028,
1033
+ "좔": 1029,
1034
+ "죄": 1030,
1035
+ "죠": 1031,
1036
+ "주": 1032,
1037
+ "죽": 1033,
1038
+ "준": 1034,
1039
+ "줄": 1035,
1040
+ "줌": 1036,
1041
+ "줍": 1037,
1042
+ "중": 1038,
1043
+ "줘": 1039,
1044
+ "줬": 1040,
1045
+ "쥐": 1041,
1046
+ "쥔": 1042,
1047
+ "쥬": 1043,
1048
+ "즈": 1044,
1049
+ "즉": 1045,
1050
+ "즌": 1046,
1051
+ "즐": 1047,
1052
+ "즘": 1048,
1053
+ "즙": 1049,
1054
+ "증": 1050,
1055
+ "지": 1051,
1056
+ "직": 1052,
1057
+ "진": 1053,
1058
+ "질": 1054,
1059
+ "짐": 1055,
1060
+ "집": 1056,
1061
+ "짓": 1057,
1062
+ "징": 1058,
1063
+ "짖": 1059,
1064
+ "짙": 1060,
1065
+ "짚": 1061,
1066
+ "짜": 1062,
1067
+ "짝": 1063,
1068
+ "짠": 1064,
1069
+ "짤": 1065,
1070
+ "짧": 1066,
1071
+ "짬": 1067,
1072
+ "짭": 1068,
1073
+ "짰": 1069,
1074
+ "짱": 1070,
1075
+ "째": 1071,
1076
+ "쨋": 1072,
1077
+ "쨌": 1073,
1078
+ "쨍": 1074,
1079
+ "쨰": 1075,
1080
+ "쩄": 1076,
1081
+ "쩌": 1077,
1082
+ "쩍": 1078,
1083
+ "쩐": 1079,
1084
+ "쩔": 1080,
1085
+ "쩜": 1081,
1086
+ "쩝": 1082,
1087
+ "쩡": 1083,
1088
+ "쪄": 1084,
1089
+ "쪘": 1085,
1090
+ "쪼": 1086,
1091
+ "쪽": 1087,
1092
+ "쫀": 1088,
1093
+ "쫄": 1089,
1094
+ "쫌": 1090,
1095
+ "쫑": 1091,
1096
+ "쫓": 1092,
1097
+ "쫘": 1093,
1098
+ "쫙": 1094,
1099
+ "쫜": 1095,
1100
+ "쫠": 1096,
1101
+ "쬐": 1097,
1102
+ "쭈": 1098,
1103
+ "쭉": 1099,
1104
+ "쭤": 1100,
1105
+ "쮸": 1101,
1106
+ "쯔": 1102,
1107
+ "쯜": 1103,
1108
+ "쯤": 1104,
1109
+ "쯧": 1105,
1110
+ "찌": 1106,
1111
+ "찍": 1107,
1112
+ "찐": 1108,
1113
+ "찔": 1109,
1114
+ "찜": 1110,
1115
+ "찝": 1111,
1116
+ "찡": 1112,
1117
+ "찢": 1113,
1118
+ "차": 1114,
1119
+ "착": 1115,
1120
+ "찬": 1116,
1121
+ "찮": 1117,
1122
+ "찰": 1118,
1123
+ "참": 1119,
1124
+ "찹": 1120,
1125
+ "찼": 1121,
1126
+ "창": 1122,
1127
+ "찾": 1123,
1128
+ "채": 1124,
1129
+ "책": 1125,
1130
+ "챔": 1126,
1131
+ "챕": 1127,
1132
+ "챙": 1128,
1133
+ "처": 1129,
1134
+ "척": 1130,
1135
+ "천": 1131,
1136
+ "철": 1132,
1137
+ "첨": 1133,
1138
+ "첩": 1134,
1139
+ "첫": 1135,
1140
+ "청": 1136,
1141
+ "체": 1137,
1142
+ "첸": 1138,
1143
+ "쳐": 1139,
1144
+ "쳤": 1140,
1145
+ "초": 1141,
1146
+ "촉": 1142,
1147
+ "촌": 1143,
1148
+ "촘": 1144,
1149
+ "총": 1145,
1150
+ "촤": 1146,
1151
+ "촥": 1147,
1152
+ "촬": 1148,
1153
+ "최": 1149,
1154
+ "쵸": 1150,
1155
+ "추": 1151,
1156
+ "축": 1152,
1157
+ "춘": 1153,
1158
+ "출": 1154,
1159
+ "춤": 1155,
1160
+ "춥": 1156,
1161
+ "춧": 1157,
1162
+ "충": 1158,
1163
+ "춰": 1159,
1164
+ "췄": 1160,
1165
+ "취": 1161,
1166
+ "츄": 1162,
1167
+ "츠": 1163,
1168
+ "측": 1164,
1169
+ "츨": 1165,
1170
+ "층": 1166,
1171
+ "치": 1167,
1172
+ "칙": 1168,
1173
+ "친": 1169,
1174
+ "칠": 1170,
1175
+ "침": 1171,
1176
+ "칩": 1172,
1177
+ "칫": 1173,
1178
+ "칭": 1174,
1179
+ "카": 1175,
1180
+ "칸": 1176,
1181
+ "칼": 1177,
1182
+ "캄": 1178,
1183
+ "캉": 1179,
1184
+ "캐": 1180,
1185
+ "캑": 1181,
1186
+ "캘": 1182,
1187
+ "캠": 1183,
1188
+ "캡": 1184,
1189
+ "캬": 1185,
1190
+ "커": 1186,
1191
+ "컨": 1187,
1192
+ "컬": 1188,
1193
+ "컴": 1189,
1194
+ "컵": 1190,
1195
+ "컷": 1191,
1196
+ "컸": 1192,
1197
+ "컹": 1193,
1198
+ "케": 1194,
1199
+ "켓": 1195,
1200
+ "켜": 1196,
1201
+ "켠": 1197,
1202
+ "켤": 1198,
1203
+ "켰": 1199,
1204
+ "코": 1200,
1205
+ "콕": 1201,
1206
+ "콘": 1202,
1207
+ "콜": 1203,
1208
+ "콤": 1204,
1209
+ "콧": 1205,
1210
+ "콩": 1206,
1211
+ "콱": 1207,
1212
+ "쾅": 1208,
1213
+ "쾌": 1209,
1214
+ "쿠": 1210,
1215
+ "쿡": 1211,
1216
+ "쿨": 1212,
1217
+ "쿰": 1213,
1218
+ "쿱": 1214,
1219
+ "쿵": 1215,
1220
+ "퀄": 1216,
1221
+ "퀴": 1217,
1222
+ "퀸": 1218,
1223
+ "큐": 1219,
1224
+ "크": 1220,
1225
+ "큰": 1221,
1226
+ "클": 1222,
1227
+ "큼": 1223,
1228
+ "큽": 1224,
1229
+ "키": 1225,
1230
+ "킨": 1226,
1231
+ "킬": 1227,
1232
+ "킴": 1228,
1233
+ "킵": 1229,
1234
+ "킷": 1230,
1235
+ "킹": 1231,
1236
+ "타": 1232,
1237
+ "탁": 1233,
1238
+ "탄": 1234,
1239
+ "탈": 1235,
1240
+ "탐": 1236,
1241
+ "탑": 1237,
1242
+ "탓": 1238,
1243
+ "탔": 1239,
1244
+ "탕": 1240,
1245
+ "태": 1241,
1246
+ "택": 1242,
1247
+ "탠": 1243,
1248
+ "탭": 1244,
1249
+ "탱": 1245,
1250
+ "터": 1246,
1251
+ "턱": 1247,
1252
+ "턴": 1248,
1253
+ "털": 1249,
1254
+ "텀": 1250,
1255
+ "텁": 1251,
1256
+ "텃": 1252,
1257
+ "텅": 1253,
1258
+ "테": 1254,
1259
+ "텍": 1255,
1260
+ "텐": 1256,
1261
+ "텔": 1257,
1262
+ "템": 1258,
1263
+ "텝": 1259,
1264
+ "텨": 1260,
1265
+ "텼": 1261,
1266
+ "토": 1262,
1267
+ "톡": 1263,
1268
+ "톤": 1264,
1269
+ "톨": 1265,
1270
+ "톰": 1266,
1271
+ "톱": 1267,
1272
+ "통": 1268,
1273
+ "퇴": 1269,
1274
+ "투": 1270,
1275
+ "툭": 1271,
1276
+ "툴": 1272,
1277
+ "툼": 1273,
1278
+ "퉁": 1274,
1279
+ "퉜": 1275,
1280
+ "튀": 1276,
1281
+ "튄": 1277,
1282
+ "튈": 1278,
1283
+ "튜": 1279,
1284
+ "트": 1280,
1285
+ "특": 1281,
1286
+ "튼": 1282,
1287
+ "틀": 1283,
1288
+ "틈": 1284,
1289
+ "티": 1285,
1290
+ "틱": 1286,
1291
+ "틴": 1287,
1292
+ "틸": 1288,
1293
+ "팀": 1289,
1294
+ "팁": 1290,
1295
+ "팅": 1291,
1296
+ "파": 1292,
1297
+ "팍": 1293,
1298
+ "팎": 1294,
1299
+ "판": 1295,
1300
+ "팔": 1296,
1301
+ "팝": 1297,
1302
+ "팟": 1298,
1303
+ "팠": 1299,
1304
+ "팡": 1300,
1305
+ "팥": 1301,
1306
+ "패": 1302,
1307
+ "팩": 1303,
1308
+ "팬": 1304,
1309
+ "팸": 1305,
1310
+ "팽": 1306,
1311
+ "퍄": 1307,
1312
+ "퍼": 1308,
1313
+ "퍽": 1309,
1314
+ "펀": 1310,
1315
+ "펄": 1311,
1316
+ "펌": 1312,
1317
+ "펐": 1313,
1318
+ "페": 1314,
1319
+ "펙": 1315,
1320
+ "펜": 1316,
1321
+ "펩": 1317,
1322
+ "펴": 1318,
1323
+ "편": 1319,
1324
+ "펼": 1320,
1325
+ "폈": 1321,
1326
+ "평": 1322,
1327
+ "폐": 1323,
1328
+ "포": 1324,
1329
+ "폭": 1325,
1330
+ "폰": 1326,
1331
+ "폴": 1327,
1332
+ "폼": 1328,
1333
+ "퐁": 1329,
1334
+ "표": 1330,
1335
+ "푸": 1331,
1336
+ "푹": 1332,
1337
+ "푼": 1333,
1338
+ "풀": 1334,
1339
+ "품": 1335,
1340
+ "풉": 1336,
1341
+ "풋": 1337,
1342
+ "풍": 1338,
1343
+ "퓨": 1339,
1344
+ "프": 1340,
1345
+ "픈": 1341,
1346
+ "플": 1342,
1347
+ "픔": 1343,
1348
+ "픕": 1344,
1349
+ "피": 1345,
1350
+ "픽": 1346,
1351
+ "핀": 1347,
1352
+ "필": 1348,
1353
+ "핏": 1349,
1354
+ "핑": 1350,
1355
+ "하": 1351,
1356
+ "학": 1352,
1357
+ "한": 1353,
1358
+ "할": 1354,
1359
+ "함": 1355,
1360
+ "합": 1356,
1361
+ "핫": 1357,
1362
+ "항": 1358,
1363
+ "해": 1359,
1364
+ "핵": 1360,
1365
+ "핸": 1361,
1366
+ "햄": 1362,
1367
+ "햅": 1363,
1368
+ "햇": 1364,
1369
+ "했": 1365,
1370
+ "행": 1366,
1371
+ "햐": 1367,
1372
+ "향": 1368,
1373
+ "허": 1369,
1374
+ "헉": 1370,
1375
+ "헐": 1371,
1376
+ "험": 1372,
1377
+ "헛": 1373,
1378
+ "헤": 1374,
1379
+ "헥": 1375,
1380
+ "헨": 1376,
1381
+ "헬": 1377,
1382
+ "헷": 1378,
1383
+ "헹": 1379,
1384
+ "혀": 1380,
1385
+ "혁": 1381,
1386
+ "현": 1382,
1387
+ "혈": 1383,
1388
+ "협": 1384,
1389
+ "혓": 1385,
1390
+ "혔": 1386,
1391
+ "형": 1387,
1392
+ "혜": 1388,
1393
+ "호": 1389,
1394
+ "혹": 1390,
1395
+ "혼": 1391,
1396
+ "홀": 1392,
1397
+ "홈": 1393,
1398
+ "홉": 1394,
1399
+ "홍": 1395,
1400
+ "화": 1396,
1401
+ "확": 1397,
1402
+ "환": 1398,
1403
+ "활": 1399,
1404
+ "황": 1400,
1405
+ "회": 1401,
1406
+ "획": 1402,
1407
+ "횐": 1403,
1408
+ "횟": 1404,
1409
+ "효": 1405,
1410
+ "횩": 1406,
1411
+ "후": 1407,
1412
+ "훅": 1408,
1413
+ "훈": 1409,
1414
+ "훌": 1410,
1415
+ "훔": 1411,
1416
+ "훨": 1412,
1417
+ "휑": 1413,
1418
+ "휘": 1414,
1419
+ "휴": 1415,
1420
+ "흉": 1416,
1421
+ "흐": 1417,
1422
+ "흑": 1418,
1423
+ "흔": 1419,
1424
+ "흘": 1420,
1425
+ "흙": 1421,
1426
+ "흠": 1422,
1427
+ "흡": 1423,
1428
+ "흣": 1424,
1429
+ "흥": 1425,
1430
+ "흩": 1426,
1431
+ "희": 1427,
1432
+ "흰": 1428,
1433
+ "히": 1429,
1434
+ "힌": 1430,
1435
+ "힐": 1431,
1436
+ "힘": 1432,
1437
+ "힙": 1433,
1438
+ "힝": 1434
1439
+ }