yesj1234 commited on
Commit
22ed128
1 Parent(s): 8d180b9

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.4651
21
+ - Cer: 0.0828
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
+ | 6.3673 | 3.17 | 1500 | 0.6104 | 0.1606 |
59
+ | 0.656 | 6.33 | 3000 | 0.4318 | 0.1129 |
60
+ | 0.4729 | 9.5 | 4500 | 0.4010 | 0.1028 |
61
+ | 0.3789 | 12.66 | 6000 | 0.3867 | 0.0977 |
62
+ | 0.3166 | 15.83 | 7500 | 0.3857 | 0.0936 |
63
+ | 0.267 | 18.99 | 9000 | 0.3891 | 0.0912 |
64
+ | 0.2286 | 22.16 | 10500 | 0.4074 | 0.0910 |
65
+ | 0.1967 | 25.32 | 12000 | 0.4079 | 0.0878 |
66
+ | 0.1712 | 28.49 | 13500 | 0.4289 | 0.0865 |
67
+ | 0.1493 | 31.65 | 15000 | 0.4456 | 0.0850 |
68
+ | 0.1333 | 34.82 | 16500 | 0.4573 | 0.0843 |
69
+ | 0.1191 | 37.98 | 18000 | 0.4633 | 0.0833 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.34.0
75
+ - Pytorch 2.0.1+cu117
76
+ - Datasets 2.14.5
77
+ - Tokenizers 0.14.0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 1306,
3
+ "<s>": 1305,
4
+ "[PAD]": 1304,
5
+ "[UNK]": 1303
6
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 39.93,
3
+ "eval_cer": 0.08284064705168438,
4
+ "eval_loss": 0.465082585811615,
5
+ "eval_runtime": 145.5339,
6
+ "eval_samples": 3770,
7
+ "eval_samples_per_second": 25.905,
8
+ "eval_steps_per_second": 3.243,
9
+ "train_loss": 0.7552054080600215,
10
+ "train_runtime": 32439.3262,
11
+ "train_samples": 30324,
12
+ "train_samples_per_second": 37.392,
13
+ "train_steps_per_second": 0.583
14
+ }
checkpoint-18000/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 1306,
3
+ "<s>": 1305,
4
+ "[PAD]": 1304,
5
+ "[UNK]": 1303
6
+ }
checkpoint-18000/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": 1304,
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": 1307,
116
+ "xvector_output_dim": 512
117
+ }
checkpoint-18000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a80a37b117b3c5b68af3d73550556525501cc3b5c78f416f89b6f3a80643d01
3
+ size 2500876673
checkpoint-18000/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-18000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c9ca1cb5763e5fe5f3641e78e623e6c63f3ecb82628173d005a81987ca7d72
3
+ size 1267260525
checkpoint-18000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32224f4070601e1063cb13ad043486e6f9fc78aed30fe6eded6307700a7df2c4
3
+ size 17655
checkpoint-18000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0651c8049b67a25edf4ab89b7d70e0b311d06b331ab7878520531f578c9b9f5c
3
+ size 17655
checkpoint-18000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e581465ca1f06e2857548192a50a00726d68129b7e2e96cf2d35e132de00b114
3
+ size 17655
checkpoint-18000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75ef618e1e573730e061b2eeab66bdf1771df515ca277c6a70b55df5aafbc46
3
+ size 17719
checkpoint-18000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f51a8c4b27e4dbaa860021fda697b04523bd25ab0bd0aaa9940b2e384233ee9
3
+ size 627
checkpoint-18000/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-18000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1303": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1304": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "1305": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "1306": {
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-18000/trainer_state.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 37.98470060670008,
5
+ "eval_steps": 1500,
6
+ "global_step": 18000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.17,
13
+ "learning_rate": 0.0002917131696428571,
14
+ "loss": 6.3673,
15
+ "step": 1500
16
+ },
17
+ {
18
+ "epoch": 3.17,
19
+ "eval_cer": 0.16064462437366714,
20
+ "eval_loss": 0.6103929877281189,
21
+ "eval_runtime": 143.9739,
22
+ "eval_samples_per_second": 26.185,
23
+ "eval_steps_per_second": 3.278,
24
+ "step": 1500
25
+ },
26
+ {
27
+ "epoch": 6.33,
28
+ "learning_rate": 0.00026660156249999997,
29
+ "loss": 0.656,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 6.33,
34
+ "eval_cer": 0.112913292993741,
35
+ "eval_loss": 0.4318251311779022,
36
+ "eval_runtime": 143.6016,
37
+ "eval_samples_per_second": 26.253,
38
+ "eval_steps_per_second": 3.287,
39
+ "step": 3000
40
+ },
41
+ {
42
+ "epoch": 9.5,
43
+ "learning_rate": 0.00024148995535714285,
44
+ "loss": 0.4729,
45
+ "step": 4500
46
+ },
47
+ {
48
+ "epoch": 9.5,
49
+ "eval_cer": 0.10276193283284499,
50
+ "eval_loss": 0.4009631276130676,
51
+ "eval_runtime": 144.1302,
52
+ "eval_samples_per_second": 26.157,
53
+ "eval_steps_per_second": 3.275,
54
+ "step": 4500
55
+ },
56
+ {
57
+ "epoch": 12.66,
58
+ "learning_rate": 0.0002163783482142857,
59
+ "loss": 0.3789,
60
+ "step": 6000
61
+ },
62
+ {
63
+ "epoch": 12.66,
64
+ "eval_cer": 0.09767324930214817,
65
+ "eval_loss": 0.3866880536079407,
66
+ "eval_runtime": 145.6008,
67
+ "eval_samples_per_second": 25.893,
68
+ "eval_steps_per_second": 3.242,
69
+ "step": 6000
70
+ },
71
+ {
72
+ "epoch": 15.83,
73
+ "learning_rate": 0.00019128348214285712,
74
+ "loss": 0.3166,
75
+ "step": 7500
76
+ },
77
+ {
78
+ "epoch": 15.83,
79
+ "eval_cer": 0.0936248417913553,
80
+ "eval_loss": 0.38572949171066284,
81
+ "eval_runtime": 144.2607,
82
+ "eval_samples_per_second": 26.133,
83
+ "eval_steps_per_second": 3.272,
84
+ "step": 7500
85
+ },
86
+ {
87
+ "epoch": 18.99,
88
+ "learning_rate": 0.00016618861607142855,
89
+ "loss": 0.267,
90
+ "step": 9000
91
+ },
92
+ {
93
+ "epoch": 18.99,
94
+ "eval_cer": 0.0911715241777485,
95
+ "eval_loss": 0.389119952917099,
96
+ "eval_runtime": 143.5612,
97
+ "eval_samples_per_second": 26.261,
98
+ "eval_steps_per_second": 3.288,
99
+ "step": 9000
100
+ },
101
+ {
102
+ "epoch": 22.16,
103
+ "learning_rate": 0.00014107700892857143,
104
+ "loss": 0.2286,
105
+ "step": 10500
106
+ },
107
+ {
108
+ "epoch": 22.16,
109
+ "eval_cer": 0.09095480000693518,
110
+ "eval_loss": 0.40744006633758545,
111
+ "eval_runtime": 143.443,
112
+ "eval_samples_per_second": 26.282,
113
+ "eval_steps_per_second": 3.291,
114
+ "step": 10500
115
+ },
116
+ {
117
+ "epoch": 25.32,
118
+ "learning_rate": 0.00011598214285714285,
119
+ "loss": 0.1967,
120
+ "step": 12000
121
+ },
122
+ {
123
+ "epoch": 25.32,
124
+ "eval_cer": 0.08783397194722332,
125
+ "eval_loss": 0.4078831076622009,
126
+ "eval_runtime": 142.9582,
127
+ "eval_samples_per_second": 26.371,
128
+ "eval_steps_per_second": 3.302,
129
+ "step": 12000
130
+ },
131
+ {
132
+ "epoch": 28.49,
133
+ "learning_rate": 9.08705357142857e-05,
134
+ "loss": 0.1712,
135
+ "step": 13500
136
+ },
137
+ {
138
+ "epoch": 28.49,
139
+ "eval_cer": 0.08651628898867833,
140
+ "eval_loss": 0.42893365025520325,
141
+ "eval_runtime": 143.8273,
142
+ "eval_samples_per_second": 26.212,
143
+ "eval_steps_per_second": 3.282,
144
+ "step": 13500
145
+ },
146
+ {
147
+ "epoch": 31.65,
148
+ "learning_rate": 6.577566964285713e-05,
149
+ "loss": 0.1493,
150
+ "step": 15000
151
+ },
152
+ {
153
+ "epoch": 31.65,
154
+ "eval_cer": 0.08501655772665014,
155
+ "eval_loss": 0.4456014931201935,
156
+ "eval_runtime": 144.3831,
157
+ "eval_samples_per_second": 26.111,
158
+ "eval_steps_per_second": 3.269,
159
+ "step": 15000
160
+ },
161
+ {
162
+ "epoch": 34.82,
163
+ "learning_rate": 4.068080357142857e-05,
164
+ "loss": 0.1333,
165
+ "step": 16500
166
+ },
167
+ {
168
+ "epoch": 34.82,
169
+ "eval_cer": 0.08429703347954991,
170
+ "eval_loss": 0.457296758890152,
171
+ "eval_runtime": 144.9279,
172
+ "eval_samples_per_second": 26.013,
173
+ "eval_steps_per_second": 3.257,
174
+ "step": 16500
175
+ },
176
+ {
177
+ "epoch": 37.98,
178
+ "learning_rate": 1.556919642857143e-05,
179
+ "loss": 0.1191,
180
+ "step": 18000
181
+ },
182
+ {
183
+ "epoch": 37.98,
184
+ "eval_cer": 0.08327409539331103,
185
+ "eval_loss": 0.4633271098136902,
186
+ "eval_runtime": 146.5025,
187
+ "eval_samples_per_second": 25.733,
188
+ "eval_steps_per_second": 3.222,
189
+ "step": 18000
190
+ }
191
+ ],
192
+ "logging_steps": 1500,
193
+ "max_steps": 18920,
194
+ "num_train_epochs": 40,
195
+ "save_steps": 1500,
196
+ "total_flos": 1.471168372274983e+20,
197
+ "trial_name": null,
198
+ "trial_params": null
199
+ }
checkpoint-18000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d5f3039b4a123f11e73fa4074522ca28a0ebf7f49ac919e5861060be565c18
3
+ size 4027
checkpoint-18000/vocab.json ADDED
@@ -0,0 +1,1307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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]": 1304,
14
+ "[UNK]": 1303,
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
+ "k": 21,
25
+ "l": 22,
26
+ "m": 23,
27
+ "n": 24,
28
+ "o": 25,
29
+ "p": 26,
30
+ "r": 27,
31
+ "s": 28,
32
+ "t": 29,
33
+ "u": 30,
34
+ "v": 31,
35
+ "w": 32,
36
+ "x": 33,
37
+ "y": 34,
38
+ "|": 0,
39
+ "ㄱ": 35,
40
+ "ㄴ": 36,
41
+ "ㄹ": 37,
42
+ "ㅁ": 38,
43
+ "ㅅ": 39,
44
+ "ㅇ": 40,
45
+ "ㅈ": 41,
46
+ "ㅋ": 42,
47
+ "가": 43,
48
+ "각": 44,
49
+ "간": 45,
50
+ "갈": 46,
51
+ "감": 47,
52
+ "갑": 48,
53
+ "값": 49,
54
+ "갓": 50,
55
+ "갔": 51,
56
+ "강": 52,
57
+ "갖": 53,
58
+ "같": 54,
59
+ "갚": 55,
60
+ "갛": 56,
61
+ "개": 57,
62
+ "객": 58,
63
+ "갠": 59,
64
+ "갤": 60,
65
+ "갰": 61,
66
+ "걍": 62,
67
+ "걔": 63,
68
+ "거": 64,
69
+ "걱": 65,
70
+ "건": 66,
71
+ "걷": 67,
72
+ "걸": 68,
73
+ "검": 69,
74
+ "겁": 70,
75
+ "것": 71,
76
+ "겉": 72,
77
+ "겋": 73,
78
+ "게": 74,
79
+ "겐": 75,
80
+ "겔": 76,
81
+ "겠": 77,
82
+ "겨": 78,
83
+ "격": 79,
84
+ "겪": 80,
85
+ "견": 81,
86
+ "결": 82,
87
+ "겸": 83,
88
+ "겹": 84,
89
+ "겼": 85,
90
+ "경": 86,
91
+ "곁": 87,
92
+ "계": 88,
93
+ "곘": 89,
94
+ "고": 90,
95
+ "곡": 91,
96
+ "곤": 92,
97
+ "곧": 93,
98
+ "골": 94,
99
+ "곰": 95,
100
+ "곱": 96,
101
+ "곳": 97,
102
+ "공": 98,
103
+ "과": 99,
104
+ "관": 100,
105
+ "괄": 101,
106
+ "광": 102,
107
+ "괜": 103,
108
+ "괴": 104,
109
+ "굉": 105,
110
+ "교": 106,
111
+ "굥": 107,
112
+ "구": 108,
113
+ "국": 109,
114
+ "군": 110,
115
+ "굳": 111,
116
+ "굴": 112,
117
+ "굵": 113,
118
+ "굶": 114,
119
+ "굽": 115,
120
+ "굿": 116,
121
+ "궁": 117,
122
+ "궈": 118,
123
+ "권": 119,
124
+ "궤": 120,
125
+ "귀": 121,
126
+ "규": 122,
127
+ "균": 123,
128
+ "귤": 124,
129
+ "그": 125,
130
+ "극": 126,
131
+ "근": 127,
132
+ "귿": 128,
133
+ "글": 129,
134
+ "긁": 130,
135
+ "금": 131,
136
+ "급": 132,
137
+ "긋": 133,
138
+ "긍": 134,
139
+ "긎": 135,
140
+ "긓": 136,
141
+ "기": 137,
142
+ "긴": 138,
143
+ "길": 139,
144
+ "김": 140,
145
+ "깁": 141,
146
+ "깃": 142,
147
+ "깊": 143,
148
+ "까": 144,
149
+ "깍": 145,
150
+ "깎": 146,
151
+ "깐": 147,
152
+ "깔": 148,
153
+ "깜": 149,
154
+ "깝": 150,
155
+ "깠": 151,
156
+ "깥": 152,
157
+ "깨": 153,
158
+ "깬": 154,
159
+ "꺼": 155,
160
+ "꺽": 156,
161
+ "껄": 157,
162
+ "껌": 158,
163
+ "껍": 159,
164
+ "껏": 160,
165
+ "껑": 161,
166
+ "께": 162,
167
+ "껴": 163,
168
+ "꼈": 164,
169
+ "꼐": 165,
170
+ "꼬": 166,
171
+ "꼭": 167,
172
+ "꼰": 168,
173
+ "꼴": 169,
174
+ "꼼": 170,
175
+ "꼽": 171,
176
+ "꽁": 172,
177
+ "꽂": 173,
178
+ "꽃": 174,
179
+ "꽈": 175,
180
+ "꽉": 176,
181
+ "꽝": 177,
182
+ "꽤": 178,
183
+ "꾸": 179,
184
+ "꾹": 180,
185
+ "꾼": 181,
186
+ "꿀": 182,
187
+ "꿈": 183,
188
+ "꿍": 184,
189
+ "꿔": 185,
190
+ "꿨": 186,
191
+ "뀌": 187,
192
+ "뀐": 188,
193
+ "뀔": 189,
194
+ "뀝": 190,
195
+ "끄": 191,
196
+ "끈": 192,
197
+ "끊": 193,
198
+ "끌": 194,
199
+ "끓": 195,
200
+ "끔": 196,
201
+ "끕": 197,
202
+ "끗": 198,
203
+ "끝": 199,
204
+ "끼": 200,
205
+ "낀": 201,
206
+ "낄": 202,
207
+ "낌": 203,
208
+ "나": 204,
209
+ "낙": 205,
210
+ "난": 206,
211
+ "날": 207,
212
+ "남": 208,
213
+ "납": 209,
214
+ "낫": 210,
215
+ "났": 211,
216
+ "낭": 212,
217
+ "낮": 213,
218
+ "낯": 214,
219
+ "낱": 215,
220
+ "낳": 216,
221
+ "내": 217,
222
+ "낸": 218,
223
+ "낼": 219,
224
+ "냄": 220,
225
+ "냅": 221,
226
+ "냈": 222,
227
+ "냉": 223,
228
+ "냐": 224,
229
+ "냥": 225,
230
+ "너": 226,
231
+ "넉": 227,
232
+ "넌": 228,
233
+ "널": 229,
234
+ "넓": 230,
235
+ "넘": 231,
236
+ "넣": 232,
237
+ "네": 233,
238
+ "넬": 234,
239
+ "넴": 235,
240
+ "넷": 236,
241
+ "녀": 237,
242
+ "녁": 238,
243
+ "년": 239,
244
+ "념": 240,
245
+ "녔": 241,
246
+ "녕": 242,
247
+ "노": 243,
248
+ "녹": 244,
249
+ "논": 245,
250
+ "놀": 246,
251
+ "놈": 247,
252
+ "농": 248,
253
+ "높": 249,
254
+ "놓": 250,
255
+ "놔": 251,
256
+ "놨": 252,
257
+ "뇌": 253,
258
+ "누": 254,
259
+ "눈": 255,
260
+ "눌": 256,
261
+ "눔": 257,
262
+ "눕": 258,
263
+ "눗": 259,
264
+ "눠": 260,
265
+ "눴": 261,
266
+ "뉘": 262,
267
+ "뉜": 263,
268
+ "뉩": 264,
269
+ "뉴": 265,
270
+ "느": 266,
271
+ "는": 267,
272
+ "늘": 268,
273
+ "늠": 269,
274
+ "능": 270,
275
+ "늦": 271,
276
+ "니": 272,
277
+ "닉": 273,
278
+ "닌": 274,
279
+ "닐": 275,
280
+ "님": 276,
281
+ "닙": 277,
282
+ "닝": 278,
283
+ "다": 279,
284
+ "닥": 280,
285
+ "닦": 281,
286
+ "단": 282,
287
+ "닫": 283,
288
+ "달": 284,
289
+ "닭": 285,
290
+ "닮": 286,
291
+ "닳": 287,
292
+ "담": 288,
293
+ "답": 289,
294
+ "닷": 290,
295
+ "당": 291,
296
+ "닿": 292,
297
+ "대": 293,
298
+ "댁": 294,
299
+ "댄": 295,
300
+ "댈": 296,
301
+ "댑": 297,
302
+ "댓": 298,
303
+ "댔": 299,
304
+ "댕": 300,
305
+ "더": 301,
306
+ "덕": 302,
307
+ "던": 303,
308
+ "덜": 304,
309
+ "덞": 305,
310
+ "덟": 306,
311
+ "덧": 307,
312
+ "덩": 308,
313
+ "덮": 309,
314
+ "데": 310,
315
+ "덱": 311,
316
+ "덴": 312,
317
+ "델": 313,
318
+ "뎀": 314,
319
+ "도": 315,
320
+ "독": 316,
321
+ "돈": 317,
322
+ "돋": 318,
323
+ "돌": 319,
324
+ "돕": 320,
325
+ "돗": 321,
326
+ "동": 322,
327
+ "돼": 323,
328
+ "됐": 324,
329
+ "되": 325,
330
+ "된": 326,
331
+ "될": 327,
332
+ "됨": 328,
333
+ "됩": 329,
334
+ "됬": 330,
335
+ "두": 331,
336
+ "둑": 332,
337
+ "둔": 333,
338
+ "둘": 334,
339
+ "둡": 335,
340
+ "둥": 336,
341
+ "둬": 337,
342
+ "뒀": 338,
343
+ "뒤": 339,
344
+ "뒷": 340,
345
+ "듀": 341,
346
+ "드": 342,
347
+ "득": 343,
348
+ "든": 344,
349
+ "듣": 345,
350
+ "들": 346,
351
+ "듦": 347,
352
+ "듬": 348,
353
+ "��": 349,
354
+ "듯": 350,
355
+ "등": 351,
356
+ "디": 352,
357
+ "딘": 353,
358
+ "딜": 354,
359
+ "딤": 355,
360
+ "딨": 356,
361
+ "딩": 357,
362
+ "딪": 358,
363
+ "따": 359,
364
+ "딱": 360,
365
+ "딴": 361,
366
+ "딸": 362,
367
+ "땀": 363,
368
+ "땅": 364,
369
+ "때": 365,
370
+ "땐": 366,
371
+ "땜": 367,
372
+ "땠": 368,
373
+ "땡": 369,
374
+ "떄": 370,
375
+ "떠": 371,
376
+ "떡": 372,
377
+ "떤": 373,
378
+ "떨": 374,
379
+ "떴": 375,
380
+ "떻": 376,
381
+ "떼": 377,
382
+ "뗀": 378,
383
+ "뗐": 379,
384
+ "또": 380,
385
+ "똑": 381,
386
+ "똥": 382,
387
+ "뚜": 383,
388
+ "뚝": 384,
389
+ "뚫": 385,
390
+ "뚱": 386,
391
+ "뛰": 387,
392
+ "뛸": 388,
393
+ "뜨": 389,
394
+ "뜬": 390,
395
+ "뜯": 391,
396
+ "뜰": 392,
397
+ "뜻": 393,
398
+ "띄": 394,
399
+ "띈": 395,
400
+ "띌": 396,
401
+ "띕": 397,
402
+ "띠": 398,
403
+ "띵": 399,
404
+ "라": 400,
405
+ "락": 401,
406
+ "란": 402,
407
+ "랄": 403,
408
+ "람": 404,
409
+ "랍": 405,
410
+ "랏": 406,
411
+ "랐": 407,
412
+ "랑": 408,
413
+ "래": 409,
414
+ "랙": 410,
415
+ "랜": 411,
416
+ "램": 412,
417
+ "랩": 413,
418
+ "랫": 414,
419
+ "랬": 415,
420
+ "략": 416,
421
+ "럈": 417,
422
+ "량": 418,
423
+ "러": 419,
424
+ "럭": 420,
425
+ "런": 421,
426
+ "럴": 422,
427
+ "럼": 423,
428
+ "럽": 424,
429
+ "렀": 425,
430
+ "렇": 426,
431
+ "레": 427,
432
+ "렌": 428,
433
+ "렛": 429,
434
+ "려": 430,
435
+ "력": 431,
436
+ "련": 432,
437
+ "렬": 433,
438
+ "렴": 434,
439
+ "렵": 435,
440
+ "렷": 436,
441
+ "렸": 437,
442
+ "령": 438,
443
+ "렼": 439,
444
+ "례": 440,
445
+ "로": 441,
446
+ "록": 442,
447
+ "론": 443,
448
+ "롤": 444,
449
+ "롬": 445,
450
+ "롭": 446,
451
+ "롯": 447,
452
+ "롱": 448,
453
+ "롷": 449,
454
+ "뢰": 450,
455
+ "료": 451,
456
+ "룡": 452,
457
+ "루": 453,
458
+ "룩": 454,
459
+ "룬": 455,
460
+ "룰": 456,
461
+ "룹": 457,
462
+ "뤄": 458,
463
+ "뤘": 459,
464
+ "류": 460,
465
+ "률": 461,
466
+ "륨": 462,
467
+ "륭": 463,
468
+ "르": 464,
469
+ "륵": 465,
470
+ "른": 466,
471
+ "를": 467,
472
+ "름": 468,
473
+ "릅": 469,
474
+ "릇": 470,
475
+ "릉": 471,
476
+ "릎": 472,
477
+ "리": 473,
478
+ "릭": 474,
479
+ "린": 475,
480
+ "릴": 476,
481
+ "림": 477,
482
+ "립": 478,
483
+ "릿": 479,
484
+ "링": 480,
485
+ "마": 481,
486
+ "막": 482,
487
+ "만": 483,
488
+ "많": 484,
489
+ "말": 485,
490
+ "맑": 486,
491
+ "맘": 487,
492
+ "맙": 488,
493
+ "맛": 489,
494
+ "망": 490,
495
+ "맞": 491,
496
+ "맡": 492,
497
+ "매": 493,
498
+ "맥": 494,
499
+ "맨": 495,
500
+ "맴": 496,
501
+ "맵": 497,
502
+ "맷": 498,
503
+ "맹": 499,
504
+ "맺": 500,
505
+ "머": 501,
506
+ "먹": 502,
507
+ "먼": 503,
508
+ "멀": 504,
509
+ "멈": 505,
510
+ "멋": 506,
511
+ "멍": 507,
512
+ "메": 508,
513
+ "멕": 509,
514
+ "멘": 510,
515
+ "멜": 511,
516
+ "멤": 512,
517
+ "며": 513,
518
+ "면": 514,
519
+ "멸": 515,
520
+ "명": 516,
521
+ "몇": 517,
522
+ "모": 518,
523
+ "목": 519,
524
+ "몫": 520,
525
+ "몬": 521,
526
+ "몰": 522,
527
+ "몸": 523,
528
+ "못": 524,
529
+ "몽": 525,
530
+ "묘": 526,
531
+ "무": 527,
532
+ "묵": 528,
533
+ "묶": 529,
534
+ "문": 530,
535
+ "묻": 531,
536
+ "물": 532,
537
+ "묽": 533,
538
+ "뭉": 534,
539
+ "뭐": 535,
540
+ "뭔": 536,
541
+ "뭘": 537,
542
+ "뭡": 538,
543
+ "뭣": 539,
544
+ "뮤": 540,
545
+ "므": 541,
546
+ "믈": 542,
547
+ "미": 543,
548
+ "믹": 544,
549
+ "민": 545,
550
+ "믿": 546,
551
+ "밀": 547,
552
+ "밈": 548,
553
+ "밌": 549,
554
+ "밍": 550,
555
+ "및": 551,
556
+ "밑": 552,
557
+ "바": 553,
558
+ "박": 554,
559
+ "밖": 555,
560
+ "반": 556,
561
+ "받": 557,
562
+ "발": 558,
563
+ "밝": 559,
564
+ "밟": 560,
565
+ "밤": 561,
566
+ "밥": 562,
567
+ "방": 563,
568
+ "배": 564,
569
+ "백": 565,
570
+ "밴": 566,
571
+ "밸": 567,
572
+ "뱁": 568,
573
+ "뱃": 569,
574
+ "뱅": 570,
575
+ "버": 571,
576
+ "벅": 572,
577
+ "번": 573,
578
+ "벌": 574,
579
+ "범": 575,
580
+ "법": 576,
581
+ "벗": 577,
582
+ "벙": 578,
583
+ "베": 579,
584
+ "벡": 580,
585
+ "벤": 581,
586
+ "벨": 582,
587
+ "벳": 583,
588
+ "벼": 584,
589
+ "벽": 585,
590
+ "변": 586,
591
+ "별": 587,
592
+ "볍": 588,
593
+ "병": 589,
594
+ "보": 590,
595
+ "복": 591,
596
+ "볶": 592,
597
+ "본": 593,
598
+ "볼": 594,
599
+ "봄": 595,
600
+ "봅": 596,
601
+ "봈": 597,
602
+ "봉": 598,
603
+ "봐": 599,
604
+ "봤": 600,
605
+ "뵌": 601,
606
+ "뵐": 602,
607
+ "뵙": 603,
608
+ "부": 604,
609
+ "북": 605,
610
+ "분": 606,
611
+ "불": 607,
612
+ "붉": 608,
613
+ "붓": 609,
614
+ "붕": 610,
615
+ "붙": 611,
616
+ "뷔": 612,
617
+ "뷰": 613,
618
+ "브": 614,
619
+ "블": 615,
620
+ "비": 616,
621
+ "빈": 617,
622
+ "빌": 618,
623
+ "빔": 619,
624
+ "빗": 620,
625
+ "빙": 621,
626
+ "빛": 622,
627
+ "빠": 623,
628
+ "빡": 624,
629
+ "빨": 625,
630
+ "빳": 626,
631
+ "빵": 627,
632
+ "빼": 628,
633
+ "빽": 629,
634
+ "뺀": 630,
635
+ "뺄": 631,
636
+ "뺏": 632,
637
+ "뺐": 633,
638
+ "뺨": 634,
639
+ "뺭": 635,
640
+ "뻐": 636,
641
+ "뻑": 637,
642
+ "뻔": 638,
643
+ "뻗": 639,
644
+ "뻘": 640,
645
+ "뻣": 641,
646
+ "뻥": 642,
647
+ "뼈": 643,
648
+ "뽀": 644,
649
+ "뽁": 645,
650
+ "뽑": 646,
651
+ "뽕": 647,
652
+ "뿌": 648,
653
+ "뿐": 649,
654
+ "뿔": 650,
655
+ "쁘": 651,
656
+ "쁜": 652,
657
+ "쁠": 653,
658
+ "쁨": 654,
659
+ "삐": 655,
660
+ "삥": 656,
661
+ "사": 657,
662
+ "삭": 658,
663
+ "산": 659,
664
+ "살": 660,
665
+ "삶": 661,
666
+ "삼": 662,
667
+ "삽": 663,
668
+ "삿": 664,
669
+ "샀": 665,
670
+ "상": 666,
671
+ "새": 667,
672
+ "색": 668,
673
+ "샌": 669,
674
+ "샐": 670,
675
+ "샘": 671,
676
+ "생": 672,
677
+ "샤": 673,
678
+ "샥": 674,
679
+ "샴": 675,
680
+ "샵": 676,
681
+ "샷": 677,
682
+ "서": 678,
683
+ "석": 679,
684
+ "섞": 680,
685
+ "선": 681,
686
+ "설": 682,
687
+ "섬": 683,
688
+ "섭": 684,
689
+ "섯": 685,
690
+ "섰": 686,
691
+ "성": 687,
692
+ "세": 688,
693
+ "센": 689,
694
+ "셀": 690,
695
+ "셈": 691,
696
+ "셉": 692,
697
+ "셋": 693,
698
+ "셌": 694,
699
+ "셔": 695,
700
+ "션": 696,
701
+ "셜": 697,
702
+ "셨": 698,
703
+ "소": 699,
704
+ "속": 700,
705
+ "손": 701,
706
+ "솔": 702,
707
+ "솜": 703,
708
+ "솟": 704,
709
+ "송": 705,
710
+ "솥": 706,
711
+ "쇄": 707,
712
+ "쇠": 708,
713
+ "쇼": 709,
714
+ "숀": 710,
715
+ "숍": 711,
716
+ "수": 712,
717
+ "숙": 713,
718
+ "순": 714,
719
+ "술": 715,
720
+ "숨": 716,
721
+ "숫": 717,
722
+ "숭": 718,
723
+ "숱": 719,
724
+ "숲": 720,
725
+ "숴": 721,
726
+ "쉐": 722,
727
+ "쉬": 723,
728
+ "쉴": 724,
729
+ "쉽": 725,
730
+ "슈": 726,
731
+ "슛": 727,
732
+ "스": 728,
733
+ "슨": 729,
734
+ "슬": 730,
735
+ "슴": 731,
736
+ "습": 732,
737
+ "슷": 733,
738
+ "승": 734,
739
+ "시": 735,
740
+ "식": 736,
741
+ "신": 737,
742
+ "싣": 738,
743
+ "실": 739,
744
+ "싫": 740,
745
+ "심": 741,
746
+ "십": 742,
747
+ "싴": 743,
748
+ "싶": 744,
749
+ "싸": 745,
750
+ "싹": 746,
751
+ "싼": 747,
752
+ "쌓": 748,
753
+ "쌤": 749,
754
+ "쌩": 750,
755
+ "쌰": 751,
756
+ "썜": 752,
757
+ "써": 753,
758
+ "썰": 754,
759
+ "썸": 755,
760
+ "썼": 756,
761
+ "쎄": 757,
762
+ "쏘": 758,
763
+ "쏙": 759,
764
+ "쏟": 760,
765
+ "쏠": 761,
766
+ "쐬": 762,
767
+ "쑥": 763,
768
+ "쓰": 764,
769
+ "쓱": 765,
770
+ "쓴": 766,
771
+ "쓸": 767,
772
+ "씀": 768,
773
+ "씁": 769,
774
+ "씌": 770,
775
+ "씨": 771,
776
+ "씩": 772,
777
+ "씬": 773,
778
+ "씹": 774,
779
+ "씻": 775,
780
+ "아": 776,
781
+ "악": 777,
782
+ "안": 778,
783
+ "앉": 779,
784
+ "않": 780,
785
+ "알": 781,
786
+ "앓": 782,
787
+ "암": 783,
788
+ "압": 784,
789
+ "앗": 785,
790
+ "았": 786,
791
+ "앙": 787,
792
+ "앞": 788,
793
+ "애": 789,
794
+ "액": 790,
795
+ "앤": 791,
796
+ "앨": 792,
797
+ "앰": 793,
798
+ "앴": 794,
799
+ "앵": 795,
800
+ "야": 796,
801
+ "약": 797,
802
+ "얀": 798,
803
+ "얇": 799,
804
+ "양": 800,
805
+ "얕": 801,
806
+ "얘": 802,
807
+ "얜": 803,
808
+ "어": 804,
809
+ "억": 805,
810
+ "언": 806,
811
+ "얹": 807,
812
+ "얻": 808,
813
+ "얼": 809,
814
+ "엄": 810,
815
+ "업": 811,
816
+ "없": 812,
817
+ "엇": 813,
818
+ "었": 814,
819
+ "엉": 815,
820
+ "엎": 816,
821
+ "에": 817,
822
+ "엑": 818,
823
+ "엔": 819,
824
+ "엘": 820,
825
+ "엠": 821,
826
+ "엣": 822,
827
+ "엥": 823,
828
+ "여": 824,
829
+ "역": 825,
830
+ "연": 826,
831
+ "열": 827,
832
+ "염": 828,
833
+ "엽": 829,
834
+ "엿": 830,
835
+ "였": 831,
836
+ "영": 832,
837
+ "옆": 833,
838
+ "예": 834,
839
+ "옛": 835,
840
+ "오": 836,
841
+ "옥": 837,
842
+ "온": 838,
843
+ "올": 839,
844
+ "옮": 840,
845
+ "옳": 841,
846
+ "옴": 842,
847
+ "옵": 843,
848
+ "옷": 844,
849
+ "옹": 845,
850
+ "와": 846,
851
+ "완": 847,
852
+ "왈": 848,
853
+ "왓": 849,
854
+ "왔": 850,
855
+ "왕": 851,
856
+ "왜": 852,
857
+ "왠": 853,
858
+ "외": 854,
859
+ "왼": 855,
860
+ "요": 856,
861
+ "욕": 857,
862
+ "용": 858,
863
+ "우": 859,
864
+ "욱": 860,
865
+ "운": 861,
866
+ "울": 862,
867
+ "움": 863,
868
+ "웁": 864,
869
+ "웃": 865,
870
+ "웅": 866,
871
+ "워": 867,
872
+ "원": 868,
873
+ "월": 869,
874
+ "웠": 870,
875
+ "웨": 871,
876
+ "웩": 872,
877
+ "웬": 873,
878
+ "웹": 874,
879
+ "위": 875,
880
+ "윈": 876,
881
+ "윗": 877,
882
+ "유": 878,
883
+ "육": 879,
884
+ "윤": 880,
885
+ "율": 881,
886
+ "융": 882,
887
+ "으": 883,
888
+ "윽": 884,
889
+ "은": 885,
890
+ "읃": 886,
891
+ "을": 887,
892
+ "음": 888,
893
+ "읍": 889,
894
+ "읏": 890,
895
+ "응": 891,
896
+ "의": 892,
897
+ "이": 893,
898
+ "익": 894,
899
+ "인": 895,
900
+ "일": 896,
901
+ "읽": 897,
902
+ "잃": 898,
903
+ "임": 899,
904
+ "입": 900,
905
+ "잇": 901,
906
+ "있": 902,
907
+ "잉": 903,
908
+ "잊": 904,
909
+ "자": 905,
910
+ "작": 906,
911
+ "잔": 907,
912
+ "잖": 908,
913
+ "잘": 909,
914
+ "잠": 910,
915
+ "잡": 911,
916
+ "잣": 912,
917
+ "장": 913,
918
+ "재": 914,
919
+ "잰": 915,
920
+ "잼": 916,
921
+ "잽": 917,
922
+ "쟁": 918,
923
+ "쟤": 919,
924
+ "저": 920,
925
+ "적": 921,
926
+ "전": 922,
927
+ "절": 923,
928
+ "젊": 924,
929
+ "점": 925,
930
+ "접": 926,
931
+ "정": 927,
932
+ "제": 928,
933
+ "젝": 929,
934
+ "젠": 930,
935
+ "젤": 931,
936
+ "져": 932,
937
+ "졌": 933,
938
+ "조": 934,
939
+ "족": 935,
940
+ "존": 936,
941
+ "졸": 937,
942
+ "좀": 938,
943
+ "좁": 939,
944
+ "종": 940,
945
+ "좋": 941,
946
+ "좌": 942,
947
+ "좔": 943,
948
+ "죄": 944,
949
+ "죠": 945,
950
+ "주": 946,
951
+ "죽": 947,
952
+ "준": 948,
953
+ "줄": 949,
954
+ "줌": 950,
955
+ "줍": 951,
956
+ "중": 952,
957
+ "줘": 953,
958
+ "줬": 954,
959
+ "쥐": 955,
960
+ "쥔": 956,
961
+ "쥬": 957,
962
+ "즈": 958,
963
+ "즉": 959,
964
+ "즌": 960,
965
+ "즐": 961,
966
+ "즘": 962,
967
+ "증": 963,
968
+ "지": 964,
969
+ "직": 965,
970
+ "진": 966,
971
+ "질": 967,
972
+ "짐": 968,
973
+ "집": 969,
974
+ "짓": 970,
975
+ "징": 971,
976
+ "짖": 972,
977
+ "짚": 973,
978
+ "짜": 974,
979
+ "짝": 975,
980
+ "짠": 976,
981
+ "짤": 977,
982
+ "짧": 978,
983
+ "짬": 979,
984
+ "짰": 980,
985
+ "짱": 981,
986
+ "째": 982,
987
+ "쨋": 983,
988
+ "쨌": 984,
989
+ "쩌": 985,
990
+ "쩍": 986,
991
+ "쩐": 987,
992
+ "쩔": 988,
993
+ "쩝": 989,
994
+ "쩠": 990,
995
+ "쪘": 991,
996
+ "쪼": 992,
997
+ "쪽": 993,
998
+ "쫀": 994,
999
+ "쫄": 995,
1000
+ "쫌": 996,
1001
+ "쫓": 997,
1002
+ "쫙": 998,
1003
+ "쭈": 999,
1004
+ "쭉": 1000,
1005
+ "쭤": 1001,
1006
+ "쮸": 1002,
1007
+ "쯤": 1003,
1008
+ "찌": 1004,
1009
+ "찍": 1005,
1010
+ "찐": 1006,
1011
+ "찔": 1007,
1012
+ "찜": 1008,
1013
+ "찝": 1009,
1014
+ "찡": 1010,
1015
+ "찢": 1011,
1016
+ "차": 1012,
1017
+ "착": 1013,
1018
+ "찬": 1014,
1019
+ "찮": 1015,
1020
+ "찰": 1016,
1021
+ "참": 1017,
1022
+ "찼": 1018,
1023
+ "창": 1019,
1024
+ "찾": 1020,
1025
+ "채": 1021,
1026
+ "책": 1022,
1027
+ "챌": 1023,
1028
+ "챕": 1024,
1029
+ "챙": 1025,
1030
+ "처": 1026,
1031
+ "척": 1027,
1032
+ "천": 1028,
1033
+ "철": 1029,
1034
+ "첨": 1030,
1035
+ "첩": 1031,
1036
+ "첫": 1032,
1037
+ "청": 1033,
1038
+ "체": 1034,
1039
+ "첼": 1035,
1040
+ "쳅": 1036,
1041
+ "쳐": 1037,
1042
+ "쳤": 1038,
1043
+ "초": 1039,
1044
+ "촉": 1040,
1045
+ "촌": 1041,
1046
+ "촘": 1042,
1047
+ "촛": 1043,
1048
+ "총": 1044,
1049
+ "촤": 1045,
1050
+ "촥": 1046,
1051
+ "촬": 1047,
1052
+ "최": 1048,
1053
+ "쵸": 1049,
1054
+ "추": 1050,
1055
+ "축": 1051,
1056
+ "춘": 1052,
1057
+ "출": 1053,
1058
+ "춤": 1054,
1059
+ "춥": 1055,
1060
+ "충": 1056,
1061
+ "춰": 1057,
1062
+ "췄": 1058,
1063
+ "췌": 1059,
1064
+ "취": 1060,
1065
+ "츠": 1061,
1066
+ "측": 1062,
1067
+ "층": 1063,
1068
+ "치": 1064,
1069
+ "칙": 1065,
1070
+ "친": 1066,
1071
+ "칠": 1067,
1072
+ "침": 1068,
1073
+ "칩": 1069,
1074
+ "칫": 1070,
1075
+ "칭": 1071,
1076
+ "카": 1072,
1077
+ "칵": 1073,
1078
+ "칸": 1074,
1079
+ "칼": 1075,
1080
+ "캉": 1076,
1081
+ "캐": 1077,
1082
+ "캔": 1078,
1083
+ "캘": 1079,
1084
+ "캠": 1080,
1085
+ "캣": 1081,
1086
+ "커": 1082,
1087
+ "컥": 1083,
1088
+ "컨": 1084,
1089
+ "컬": 1085,
1090
+ "컴": 1086,
1091
+ "컵": 1087,
1092
+ "컷": 1088,
1093
+ "컸": 1089,
1094
+ "케": 1090,
1095
+ "켓": 1091,
1096
+ "켜": 1092,
1097
+ "켰": 1093,
1098
+ "코": 1094,
1099
+ "콕": 1095,
1100
+ "콘": 1096,
1101
+ "콜": 1097,
1102
+ "콤": 1098,
1103
+ "콥": 1099,
1104
+ "콧": 1100,
1105
+ "콩": 1101,
1106
+ "콸": 1102,
1107
+ "쾌": 1103,
1108
+ "쿠": 1104,
1109
+ "쿤": 1105,
1110
+ "쿨": 1106,
1111
+ "퀄": 1107,
1112
+ "퀴": 1108,
1113
+ "큐": 1109,
1114
+ "큘": 1110,
1115
+ "크": 1111,
1116
+ "큰": 1112,
1117
+ "클": 1113,
1118
+ "큼": 1114,
1119
+ "큽": 1115,
1120
+ "키": 1116,
1121
+ "킨": 1117,
1122
+ "킬": 1118,
1123
+ "킴": 1119,
1124
+ "킵": 1120,
1125
+ "타": 1121,
1126
+ "탁": 1122,
1127
+ "탄": 1123,
1128
+ "탈": 1124,
1129
+ "탐": 1125,
1130
+ "탑": 1126,
1131
+ "탓": 1127,
1132
+ "탔": 1128,
1133
+ "탕": 1129,
1134
+ "태": 1130,
1135
+ "택": 1131,
1136
+ "탠": 1132,
1137
+ "탱": 1133,
1138
+ "터": 1134,
1139
+ "턱": 1135,
1140
+ "턴": 1136,
1141
+ "털": 1137,
1142
+ "텅": 1138,
1143
+ "테": 1139,
1144
+ "텍": 1140,
1145
+ "텐": 1141,
1146
+ "텔": 1142,
1147
+ "템": 1143,
1148
+ "텝": 1144,
1149
+ "토": 1145,
1150
+ "톡": 1146,
1151
+ "톤": 1147,
1152
+ "톨": 1148,
1153
+ "톱": 1149,
1154
+ "통": 1150,
1155
+ "퇴": 1151,
1156
+ "투": 1152,
1157
+ "툭": 1153,
1158
+ "툴": 1154,
1159
+ "툼": 1155,
1160
+ "튀": 1156,
1161
+ "튜": 1157,
1162
+ "트": 1158,
1163
+ "특": 1159,
1164
+ "튼": 1160,
1165
+ "틀": 1161,
1166
+ "틈": 1162,
1167
+ "틍": 1163,
1168
+ "티": 1164,
1169
+ "틱": 1165,
1170
+ "틴": 1166,
1171
+ "틸": 1167,
1172
+ "팀": 1168,
1173
+ "팁": 1169,
1174
+ "팅": 1170,
1175
+ "파": 1171,
1176
+ "팍": 1172,
1177
+ "팎": 1173,
1178
+ "판": 1174,
1179
+ "팔": 1175,
1180
+ "팜": 1176,
1181
+ "팠": 1177,
1182
+ "팥": 1178,
1183
+ "패": 1179,
1184
+ "팩": 1180,
1185
+ "팬": 1181,
1186
+ "팽": 1182,
1187
+ "퍼": 1183,
1188
+ "퍽": 1184,
1189
+ "펀": 1185,
1190
+ "펌": 1186,
1191
+ "페": 1187,
1192
+ "펙": 1188,
1193
+ "펜": 1189,
1194
+ "펠": 1190,
1195
+ "펩": 1191,
1196
+ "펴": 1192,
1197
+ "편": 1193,
1198
+ "펼": 1194,
1199
+ "폈": 1195,
1200
+ "평": 1196,
1201
+ "폐": 1197,
1202
+ "포": 1198,
1203
+ "폭": 1199,
1204
+ "폰": 1200,
1205
+ "폴": 1201,
1206
+ "폼": 1202,
1207
+ "표": 1203,
1208
+ "푸": 1204,
1209
+ "푹": 1205,
1210
+ "푼": 1206,
1211
+ "풀": 1207,
1212
+ "품": 1208,
1213
+ "풋": 1209,
1214
+ "풍": 1210,
1215
+ "퓨": 1211,
1216
+ "프": 1212,
1217
+ "픈": 1213,
1218
+ "플": 1214,
1219
+ "픔": 1215,
1220
+ "피": 1216,
1221
+ "핀": 1217,
1222
+ "필": 1218,
1223
+ "핌": 1219,
1224
+ "핍": 1220,
1225
+ "핑": 1221,
1226
+ "하": 1222,
1227
+ "학": 1223,
1228
+ "한": 1224,
1229
+ "할": 1225,
1230
+ "함": 1226,
1231
+ "합": 1227,
1232
+ "핫": 1228,
1233
+ "항": 1229,
1234
+ "해": 1230,
1235
+ "핵": 1231,
1236
+ "핸": 1232,
1237
+ "햅": 1233,
1238
+ "햇": 1234,
1239
+ "했": 1235,
1240
+ "행": 1236,
1241
+ "햍": 1237,
1242
+ "향": 1238,
1243
+ "헀": 1239,
1244
+ "허": 1240,
1245
+ "헉": 1241,
1246
+ "헌": 1242,
1247
+ "헐": 1243,
1248
+ "험": 1244,
1249
+ "헛": 1245,
1250
+ "헝": 1246,
1251
+ "헤": 1247,
1252
+ "헨": 1248,
1253
+ "헷": 1249,
1254
+ "헹": 1250,
1255
+ "혀": 1251,
1256
+ "혁": 1252,
1257
+ "현": 1253,
1258
+ "혈": 1254,
1259
+ "혐": 1255,
1260
+ "협": 1256,
1261
+ "혔": 1257,
1262
+ "형": 1258,
1263
+ "혜": 1259,
1264
+ "호": 1260,
1265
+ "혹": 1261,
1266
+ "혼": 1262,
1267
+ "홀": 1263,
1268
+ "홈": 1264,
1269
+ "홉": 1265,
1270
+ "홍": 1266,
1271
+ "화": 1267,
1272
+ "확": 1268,
1273
+ "환": 1269,
1274
+ "활": 1270,
1275
+ "황": 1271,
1276
+ "회": 1272,
1277
+ "획": 1273,
1278
+ "횟": 1274,
1279
+ "횡": 1275,
1280
+ "효": 1276,
1281
+ "후": 1277,
1282
+ "훈": 1278,
1283
+ "훌": 1279,
1284
+ "훑": 1280,
1285
+ "훨": 1281,
1286
+ "훼": 1282,
1287
+ "휘": 1283,
1288
+ "휙": 1284,
1289
+ "휩": 1285,
1290
+ "휴": 1286,
1291
+ "흉": 1287,
1292
+ "흐": 1288,
1293
+ "흑": 1289,
1294
+ "흔": 1290,
1295
+ "흘": 1291,
1296
+ "흙": 1292,
1297
+ "흠": 1293,
1298
+ "흡": 1294,
1299
+ "흥": 1295,
1300
+ "흩": 1296,
1301
+ "희": 1297,
1302
+ "흰": 1298,
1303
+ "히": 1299,
1304
+ "힌": 1300,
1305
+ "힐": 1301,
1306
+ "힘": 1302
1307
+ }
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": 1304,
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": 1307,
116
+ "xvector_output_dim": 512
117
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 39.93,
3
+ "eval_cer": 0.08284064705168438,
4
+ "eval_loss": 0.465082585811615,
5
+ "eval_runtime": 145.5339,
6
+ "eval_samples": 3770,
7
+ "eval_samples_per_second": 25.905,
8
+ "eval_steps_per_second": 3.243
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 sha256:2d30dd75bf011f5ba7eeb6e61a674bc4afdb521fb90174803a87bc5649932610
3
+ size 1267260525
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
+ "1303": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1304": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "1305": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "1306": {
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": 39.93,
3
+ "train_loss": 0.7552054080600215,
4
+ "train_runtime": 32439.3262,
5
+ "train_samples": 30324,
6
+ "train_samples_per_second": 37.392,
7
+ "train_steps_per_second": 0.583
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 39.926140859931415,
5
+ "eval_steps": 1500,
6
+ "global_step": 18920,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.17,
13
+ "learning_rate": 0.0002917131696428571,
14
+ "loss": 6.3673,
15
+ "step": 1500
16
+ },
17
+ {
18
+ "epoch": 3.17,
19
+ "eval_cer": 0.16064462437366714,
20
+ "eval_loss": 0.6103929877281189,
21
+ "eval_runtime": 143.9739,
22
+ "eval_samples_per_second": 26.185,
23
+ "eval_steps_per_second": 3.278,
24
+ "step": 1500
25
+ },
26
+ {
27
+ "epoch": 6.33,
28
+ "learning_rate": 0.00026660156249999997,
29
+ "loss": 0.656,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 6.33,
34
+ "eval_cer": 0.112913292993741,
35
+ "eval_loss": 0.4318251311779022,
36
+ "eval_runtime": 143.6016,
37
+ "eval_samples_per_second": 26.253,
38
+ "eval_steps_per_second": 3.287,
39
+ "step": 3000
40
+ },
41
+ {
42
+ "epoch": 9.5,
43
+ "learning_rate": 0.00024148995535714285,
44
+ "loss": 0.4729,
45
+ "step": 4500
46
+ },
47
+ {
48
+ "epoch": 9.5,
49
+ "eval_cer": 0.10276193283284499,
50
+ "eval_loss": 0.4009631276130676,
51
+ "eval_runtime": 144.1302,
52
+ "eval_samples_per_second": 26.157,
53
+ "eval_steps_per_second": 3.275,
54
+ "step": 4500
55
+ },
56
+ {
57
+ "epoch": 12.66,
58
+ "learning_rate": 0.0002163783482142857,
59
+ "loss": 0.3789,
60
+ "step": 6000
61
+ },
62
+ {
63
+ "epoch": 12.66,
64
+ "eval_cer": 0.09767324930214817,
65
+ "eval_loss": 0.3866880536079407,
66
+ "eval_runtime": 145.6008,
67
+ "eval_samples_per_second": 25.893,
68
+ "eval_steps_per_second": 3.242,
69
+ "step": 6000
70
+ },
71
+ {
72
+ "epoch": 15.83,
73
+ "learning_rate": 0.00019128348214285712,
74
+ "loss": 0.3166,
75
+ "step": 7500
76
+ },
77
+ {
78
+ "epoch": 15.83,
79
+ "eval_cer": 0.0936248417913553,
80
+ "eval_loss": 0.38572949171066284,
81
+ "eval_runtime": 144.2607,
82
+ "eval_samples_per_second": 26.133,
83
+ "eval_steps_per_second": 3.272,
84
+ "step": 7500
85
+ },
86
+ {
87
+ "epoch": 18.99,
88
+ "learning_rate": 0.00016618861607142855,
89
+ "loss": 0.267,
90
+ "step": 9000
91
+ },
92
+ {
93
+ "epoch": 18.99,
94
+ "eval_cer": 0.0911715241777485,
95
+ "eval_loss": 0.389119952917099,
96
+ "eval_runtime": 143.5612,
97
+ "eval_samples_per_second": 26.261,
98
+ "eval_steps_per_second": 3.288,
99
+ "step": 9000
100
+ },
101
+ {
102
+ "epoch": 22.16,
103
+ "learning_rate": 0.00014107700892857143,
104
+ "loss": 0.2286,
105
+ "step": 10500
106
+ },
107
+ {
108
+ "epoch": 22.16,
109
+ "eval_cer": 0.09095480000693518,
110
+ "eval_loss": 0.40744006633758545,
111
+ "eval_runtime": 143.443,
112
+ "eval_samples_per_second": 26.282,
113
+ "eval_steps_per_second": 3.291,
114
+ "step": 10500
115
+ },
116
+ {
117
+ "epoch": 25.32,
118
+ "learning_rate": 0.00011598214285714285,
119
+ "loss": 0.1967,
120
+ "step": 12000
121
+ },
122
+ {
123
+ "epoch": 25.32,
124
+ "eval_cer": 0.08783397194722332,
125
+ "eval_loss": 0.4078831076622009,
126
+ "eval_runtime": 142.9582,
127
+ "eval_samples_per_second": 26.371,
128
+ "eval_steps_per_second": 3.302,
129
+ "step": 12000
130
+ },
131
+ {
132
+ "epoch": 28.49,
133
+ "learning_rate": 9.08705357142857e-05,
134
+ "loss": 0.1712,
135
+ "step": 13500
136
+ },
137
+ {
138
+ "epoch": 28.49,
139
+ "eval_cer": 0.08651628898867833,
140
+ "eval_loss": 0.42893365025520325,
141
+ "eval_runtime": 143.8273,
142
+ "eval_samples_per_second": 26.212,
143
+ "eval_steps_per_second": 3.282,
144
+ "step": 13500
145
+ },
146
+ {
147
+ "epoch": 31.65,
148
+ "learning_rate": 6.577566964285713e-05,
149
+ "loss": 0.1493,
150
+ "step": 15000
151
+ },
152
+ {
153
+ "epoch": 31.65,
154
+ "eval_cer": 0.08501655772665014,
155
+ "eval_loss": 0.4456014931201935,
156
+ "eval_runtime": 144.3831,
157
+ "eval_samples_per_second": 26.111,
158
+ "eval_steps_per_second": 3.269,
159
+ "step": 15000
160
+ },
161
+ {
162
+ "epoch": 34.82,
163
+ "learning_rate": 4.068080357142857e-05,
164
+ "loss": 0.1333,
165
+ "step": 16500
166
+ },
167
+ {
168
+ "epoch": 34.82,
169
+ "eval_cer": 0.08429703347954991,
170
+ "eval_loss": 0.457296758890152,
171
+ "eval_runtime": 144.9279,
172
+ "eval_samples_per_second": 26.013,
173
+ "eval_steps_per_second": 3.257,
174
+ "step": 16500
175
+ },
176
+ {
177
+ "epoch": 37.98,
178
+ "learning_rate": 1.556919642857143e-05,
179
+ "loss": 0.1191,
180
+ "step": 18000
181
+ },
182
+ {
183
+ "epoch": 37.98,
184
+ "eval_cer": 0.08327409539331103,
185
+ "eval_loss": 0.4633271098136902,
186
+ "eval_runtime": 146.5025,
187
+ "eval_samples_per_second": 25.733,
188
+ "eval_steps_per_second": 3.222,
189
+ "step": 18000
190
+ },
191
+ {
192
+ "epoch": 39.93,
193
+ "step": 18920,
194
+ "total_flos": 1.5462553297546432e+20,
195
+ "train_loss": 0.7552054080600215,
196
+ "train_runtime": 32439.3262,
197
+ "train_samples_per_second": 37.392,
198
+ "train_steps_per_second": 0.583
199
+ }
200
+ ],
201
+ "logging_steps": 1500,
202
+ "max_steps": 18920,
203
+ "num_train_epochs": 40,
204
+ "save_steps": 1500,
205
+ "total_flos": 1.5462553297546432e+20,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d5f3039b4a123f11e73fa4074522ca28a0ebf7f49ac919e5861060be565c18
3
+ size 4027
vocab.json ADDED
@@ -0,0 +1,1307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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]": 1304,
14
+ "[UNK]": 1303,
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
+ "k": 21,
25
+ "l": 22,
26
+ "m": 23,
27
+ "n": 24,
28
+ "o": 25,
29
+ "p": 26,
30
+ "r": 27,
31
+ "s": 28,
32
+ "t": 29,
33
+ "u": 30,
34
+ "v": 31,
35
+ "w": 32,
36
+ "x": 33,
37
+ "y": 34,
38
+ "|": 0,
39
+ "ㄱ": 35,
40
+ "ㄴ": 36,
41
+ "ㄹ": 37,
42
+ "ㅁ": 38,
43
+ "ㅅ": 39,
44
+ "ㅇ": 40,
45
+ "ㅈ": 41,
46
+ "ㅋ": 42,
47
+ "가": 43,
48
+ "각": 44,
49
+ "간": 45,
50
+ "갈": 46,
51
+ "감": 47,
52
+ "갑": 48,
53
+ "값": 49,
54
+ "갓": 50,
55
+ "갔": 51,
56
+ "강": 52,
57
+ "갖": 53,
58
+ "같": 54,
59
+ "갚": 55,
60
+ "갛": 56,
61
+ "개": 57,
62
+ "객": 58,
63
+ "갠": 59,
64
+ "갤": 60,
65
+ "갰": 61,
66
+ "걍": 62,
67
+ "걔": 63,
68
+ "거": 64,
69
+ "걱": 65,
70
+ "건": 66,
71
+ "걷": 67,
72
+ "걸": 68,
73
+ "검": 69,
74
+ "겁": 70,
75
+ "것": 71,
76
+ "겉": 72,
77
+ "겋": 73,
78
+ "게": 74,
79
+ "겐": 75,
80
+ "겔": 76,
81
+ "겠": 77,
82
+ "겨": 78,
83
+ "격": 79,
84
+ "겪": 80,
85
+ "견": 81,
86
+ "결": 82,
87
+ "겸": 83,
88
+ "겹": 84,
89
+ "겼": 85,
90
+ "경": 86,
91
+ "곁": 87,
92
+ "계": 88,
93
+ "곘": 89,
94
+ "고": 90,
95
+ "곡": 91,
96
+ "곤": 92,
97
+ "곧": 93,
98
+ "골": 94,
99
+ "곰": 95,
100
+ "곱": 96,
101
+ "곳": 97,
102
+ "공": 98,
103
+ "과": 99,
104
+ "관": 100,
105
+ "괄": 101,
106
+ "광": 102,
107
+ "괜": 103,
108
+ "괴": 104,
109
+ "굉": 105,
110
+ "교": 106,
111
+ "굥": 107,
112
+ "구": 108,
113
+ "국": 109,
114
+ "군": 110,
115
+ "굳": 111,
116
+ "굴": 112,
117
+ "굵": 113,
118
+ "굶": 114,
119
+ "굽": 115,
120
+ "굿": 116,
121
+ "궁": 117,
122
+ "궈": 118,
123
+ "권": 119,
124
+ "궤": 120,
125
+ "귀": 121,
126
+ "규": 122,
127
+ "균": 123,
128
+ "귤": 124,
129
+ "그": 125,
130
+ "극": 126,
131
+ "근": 127,
132
+ "귿": 128,
133
+ "글": 129,
134
+ "긁": 130,
135
+ "금": 131,
136
+ "급": 132,
137
+ "긋": 133,
138
+ "긍": 134,
139
+ "긎": 135,
140
+ "긓": 136,
141
+ "기": 137,
142
+ "긴": 138,
143
+ "길": 139,
144
+ "김": 140,
145
+ "깁": 141,
146
+ "깃": 142,
147
+ "깊": 143,
148
+ "까": 144,
149
+ "깍": 145,
150
+ "깎": 146,
151
+ "깐": 147,
152
+ "깔": 148,
153
+ "깜": 149,
154
+ "깝": 150,
155
+ "깠": 151,
156
+ "깥": 152,
157
+ "깨": 153,
158
+ "깬": 154,
159
+ "꺼": 155,
160
+ "꺽": 156,
161
+ "껄": 157,
162
+ "껌": 158,
163
+ "껍": 159,
164
+ "껏": 160,
165
+ "껑": 161,
166
+ "께": 162,
167
+ "껴": 163,
168
+ "꼈": 164,
169
+ "꼐": 165,
170
+ "꼬": 166,
171
+ "꼭": 167,
172
+ "꼰": 168,
173
+ "꼴": 169,
174
+ "꼼": 170,
175
+ "꼽": 171,
176
+ "꽁": 172,
177
+ "꽂": 173,
178
+ "꽃": 174,
179
+ "꽈": 175,
180
+ "꽉": 176,
181
+ "꽝": 177,
182
+ "꽤": 178,
183
+ "꾸": 179,
184
+ "꾹": 180,
185
+ "꾼": 181,
186
+ "꿀": 182,
187
+ "꿈": 183,
188
+ "꿍": 184,
189
+ "꿔": 185,
190
+ "꿨": 186,
191
+ "뀌": 187,
192
+ "뀐": 188,
193
+ "뀔": 189,
194
+ "뀝": 190,
195
+ "끄": 191,
196
+ "끈": 192,
197
+ "끊": 193,
198
+ "끌": 194,
199
+ "끓": 195,
200
+ "끔": 196,
201
+ "끕": 197,
202
+ "끗": 198,
203
+ "끝": 199,
204
+ "끼": 200,
205
+ "낀": 201,
206
+ "낄": 202,
207
+ "낌": 203,
208
+ "나": 204,
209
+ "낙": 205,
210
+ "난": 206,
211
+ "날": 207,
212
+ "남": 208,
213
+ "납": 209,
214
+ "낫": 210,
215
+ "났": 211,
216
+ "낭": 212,
217
+ "낮": 213,
218
+ "낯": 214,
219
+ "낱": 215,
220
+ "낳": 216,
221
+ "내": 217,
222
+ "낸": 218,
223
+ "낼": 219,
224
+ "냄": 220,
225
+ "냅": 221,
226
+ "냈": 222,
227
+ "냉": 223,
228
+ "냐": 224,
229
+ "냥": 225,
230
+ "너": 226,
231
+ "넉": 227,
232
+ "넌": 228,
233
+ "널": 229,
234
+ "넓": 230,
235
+ "넘": 231,
236
+ "넣": 232,
237
+ "네": 233,
238
+ "넬": 234,
239
+ "넴": 235,
240
+ "넷": 236,
241
+ "녀": 237,
242
+ "녁": 238,
243
+ "년": 239,
244
+ "념": 240,
245
+ "녔": 241,
246
+ "녕": 242,
247
+ "노": 243,
248
+ "녹": 244,
249
+ "논": 245,
250
+ "놀": 246,
251
+ "놈": 247,
252
+ "농": 248,
253
+ "높": 249,
254
+ "놓": 250,
255
+ "놔": 251,
256
+ "놨": 252,
257
+ "뇌": 253,
258
+ "누": 254,
259
+ "눈": 255,
260
+ "눌": 256,
261
+ "눔": 257,
262
+ "눕": 258,
263
+ "눗": 259,
264
+ "눠": 260,
265
+ "눴": 261,
266
+ "뉘": 262,
267
+ "뉜": 263,
268
+ "뉩": 264,
269
+ "뉴": 265,
270
+ "느": 266,
271
+ "는": 267,
272
+ "늘": 268,
273
+ "늠": 269,
274
+ "능": 270,
275
+ "늦": 271,
276
+ "니": 272,
277
+ "닉": 273,
278
+ "닌": 274,
279
+ "닐": 275,
280
+ "님": 276,
281
+ "닙": 277,
282
+ "닝": 278,
283
+ "다": 279,
284
+ "닥": 280,
285
+ "닦": 281,
286
+ "단": 282,
287
+ "닫": 283,
288
+ "달": 284,
289
+ "닭": 285,
290
+ "닮": 286,
291
+ "닳": 287,
292
+ "담": 288,
293
+ "답": 289,
294
+ "닷": 290,
295
+ "당": 291,
296
+ "닿": 292,
297
+ "대": 293,
298
+ "댁": 294,
299
+ "댄": 295,
300
+ "댈": 296,
301
+ "댑": 297,
302
+ "댓": 298,
303
+ "댔": 299,
304
+ "댕": 300,
305
+ "더": 301,
306
+ "덕": 302,
307
+ "던": 303,
308
+ "덜": 304,
309
+ "덞": 305,
310
+ "덟": 306,
311
+ "덧": 307,
312
+ "덩": 308,
313
+ "덮": 309,
314
+ "데": 310,
315
+ "덱": 311,
316
+ "덴": 312,
317
+ "델": 313,
318
+ "뎀": 314,
319
+ "도": 315,
320
+ "독": 316,
321
+ "돈": 317,
322
+ "돋": 318,
323
+ "돌": 319,
324
+ "돕": 320,
325
+ "돗": 321,
326
+ "동": 322,
327
+ "돼": 323,
328
+ "됐": 324,
329
+ "되": 325,
330
+ "된": 326,
331
+ "될": 327,
332
+ "됨": 328,
333
+ "됩": 329,
334
+ "됬": 330,
335
+ "두": 331,
336
+ "둑": 332,
337
+ "둔": 333,
338
+ "둘": 334,
339
+ "둡": 335,
340
+ "둥": 336,
341
+ "둬": 337,
342
+ "뒀": 338,
343
+ "뒤": 339,
344
+ "뒷": 340,
345
+ "듀": 341,
346
+ "드": 342,
347
+ "득": 343,
348
+ "든": 344,
349
+ "듣": 345,
350
+ "들": 346,
351
+ "듦": 347,
352
+ "듬": 348,
353
+ "��": 349,
354
+ "듯": 350,
355
+ "등": 351,
356
+ "디": 352,
357
+ "딘": 353,
358
+ "딜": 354,
359
+ "딤": 355,
360
+ "딨": 356,
361
+ "딩": 357,
362
+ "딪": 358,
363
+ "따": 359,
364
+ "딱": 360,
365
+ "딴": 361,
366
+ "딸": 362,
367
+ "땀": 363,
368
+ "땅": 364,
369
+ "때": 365,
370
+ "땐": 366,
371
+ "땜": 367,
372
+ "땠": 368,
373
+ "땡": 369,
374
+ "떄": 370,
375
+ "떠": 371,
376
+ "떡": 372,
377
+ "떤": 373,
378
+ "떨": 374,
379
+ "떴": 375,
380
+ "떻": 376,
381
+ "떼": 377,
382
+ "뗀": 378,
383
+ "뗐": 379,
384
+ "또": 380,
385
+ "똑": 381,
386
+ "똥": 382,
387
+ "뚜": 383,
388
+ "뚝": 384,
389
+ "뚫": 385,
390
+ "뚱": 386,
391
+ "뛰": 387,
392
+ "뛸": 388,
393
+ "뜨": 389,
394
+ "뜬": 390,
395
+ "뜯": 391,
396
+ "뜰": 392,
397
+ "뜻": 393,
398
+ "띄": 394,
399
+ "띈": 395,
400
+ "띌": 396,
401
+ "띕": 397,
402
+ "띠": 398,
403
+ "띵": 399,
404
+ "라": 400,
405
+ "락": 401,
406
+ "란": 402,
407
+ "랄": 403,
408
+ "람": 404,
409
+ "랍": 405,
410
+ "랏": 406,
411
+ "랐": 407,
412
+ "랑": 408,
413
+ "래": 409,
414
+ "랙": 410,
415
+ "랜": 411,
416
+ "램": 412,
417
+ "랩": 413,
418
+ "랫": 414,
419
+ "랬": 415,
420
+ "략": 416,
421
+ "럈": 417,
422
+ "량": 418,
423
+ "러": 419,
424
+ "럭": 420,
425
+ "런": 421,
426
+ "럴": 422,
427
+ "럼": 423,
428
+ "럽": 424,
429
+ "렀": 425,
430
+ "렇": 426,
431
+ "레": 427,
432
+ "렌": 428,
433
+ "렛": 429,
434
+ "려": 430,
435
+ "력": 431,
436
+ "련": 432,
437
+ "렬": 433,
438
+ "렴": 434,
439
+ "렵": 435,
440
+ "렷": 436,
441
+ "렸": 437,
442
+ "령": 438,
443
+ "렼": 439,
444
+ "례": 440,
445
+ "로": 441,
446
+ "록": 442,
447
+ "론": 443,
448
+ "롤": 444,
449
+ "롬": 445,
450
+ "롭": 446,
451
+ "롯": 447,
452
+ "롱": 448,
453
+ "롷": 449,
454
+ "뢰": 450,
455
+ "료": 451,
456
+ "룡": 452,
457
+ "루": 453,
458
+ "룩": 454,
459
+ "룬": 455,
460
+ "룰": 456,
461
+ "룹": 457,
462
+ "뤄": 458,
463
+ "뤘": 459,
464
+ "류": 460,
465
+ "률": 461,
466
+ "륨": 462,
467
+ "륭": 463,
468
+ "르": 464,
469
+ "륵": 465,
470
+ "른": 466,
471
+ "를": 467,
472
+ "름": 468,
473
+ "릅": 469,
474
+ "릇": 470,
475
+ "릉": 471,
476
+ "릎": 472,
477
+ "리": 473,
478
+ "릭": 474,
479
+ "린": 475,
480
+ "릴": 476,
481
+ "림": 477,
482
+ "립": 478,
483
+ "릿": 479,
484
+ "링": 480,
485
+ "마": 481,
486
+ "막": 482,
487
+ "만": 483,
488
+ "많": 484,
489
+ "말": 485,
490
+ "맑": 486,
491
+ "맘": 487,
492
+ "맙": 488,
493
+ "맛": 489,
494
+ "망": 490,
495
+ "맞": 491,
496
+ "맡": 492,
497
+ "매": 493,
498
+ "맥": 494,
499
+ "맨": 495,
500
+ "맴": 496,
501
+ "맵": 497,
502
+ "맷": 498,
503
+ "맹": 499,
504
+ "맺": 500,
505
+ "머": 501,
506
+ "먹": 502,
507
+ "먼": 503,
508
+ "멀": 504,
509
+ "멈": 505,
510
+ "멋": 506,
511
+ "멍": 507,
512
+ "메": 508,
513
+ "멕": 509,
514
+ "멘": 510,
515
+ "멜": 511,
516
+ "멤": 512,
517
+ "며": 513,
518
+ "면": 514,
519
+ "멸": 515,
520
+ "명": 516,
521
+ "몇": 517,
522
+ "모": 518,
523
+ "목": 519,
524
+ "몫": 520,
525
+ "몬": 521,
526
+ "몰": 522,
527
+ "몸": 523,
528
+ "못": 524,
529
+ "몽": 525,
530
+ "묘": 526,
531
+ "무": 527,
532
+ "묵": 528,
533
+ "묶": 529,
534
+ "문": 530,
535
+ "묻": 531,
536
+ "물": 532,
537
+ "묽": 533,
538
+ "뭉": 534,
539
+ "뭐": 535,
540
+ "뭔": 536,
541
+ "뭘": 537,
542
+ "뭡": 538,
543
+ "뭣": 539,
544
+ "뮤": 540,
545
+ "므": 541,
546
+ "믈": 542,
547
+ "미": 543,
548
+ "믹": 544,
549
+ "민": 545,
550
+ "믿": 546,
551
+ "밀": 547,
552
+ "밈": 548,
553
+ "밌": 549,
554
+ "밍": 550,
555
+ "및": 551,
556
+ "밑": 552,
557
+ "바": 553,
558
+ "박": 554,
559
+ "밖": 555,
560
+ "반": 556,
561
+ "받": 557,
562
+ "발": 558,
563
+ "밝": 559,
564
+ "밟": 560,
565
+ "밤": 561,
566
+ "밥": 562,
567
+ "방": 563,
568
+ "배": 564,
569
+ "백": 565,
570
+ "밴": 566,
571
+ "밸": 567,
572
+ "뱁": 568,
573
+ "뱃": 569,
574
+ "뱅": 570,
575
+ "버": 571,
576
+ "벅": 572,
577
+ "번": 573,
578
+ "벌": 574,
579
+ "범": 575,
580
+ "법": 576,
581
+ "벗": 577,
582
+ "벙": 578,
583
+ "베": 579,
584
+ "벡": 580,
585
+ "벤": 581,
586
+ "벨": 582,
587
+ "벳": 583,
588
+ "벼": 584,
589
+ "벽": 585,
590
+ "변": 586,
591
+ "별": 587,
592
+ "볍": 588,
593
+ "병": 589,
594
+ "보": 590,
595
+ "복": 591,
596
+ "볶": 592,
597
+ "본": 593,
598
+ "볼": 594,
599
+ "봄": 595,
600
+ "봅": 596,
601
+ "봈": 597,
602
+ "봉": 598,
603
+ "봐": 599,
604
+ "봤": 600,
605
+ "뵌": 601,
606
+ "뵐": 602,
607
+ "뵙": 603,
608
+ "부": 604,
609
+ "북": 605,
610
+ "분": 606,
611
+ "불": 607,
612
+ "붉": 608,
613
+ "붓": 609,
614
+ "붕": 610,
615
+ "붙": 611,
616
+ "뷔": 612,
617
+ "뷰": 613,
618
+ "브": 614,
619
+ "블": 615,
620
+ "비": 616,
621
+ "빈": 617,
622
+ "빌": 618,
623
+ "빔": 619,
624
+ "빗": 620,
625
+ "빙": 621,
626
+ "빛": 622,
627
+ "빠": 623,
628
+ "빡": 624,
629
+ "빨": 625,
630
+ "빳": 626,
631
+ "빵": 627,
632
+ "빼": 628,
633
+ "빽": 629,
634
+ "뺀": 630,
635
+ "뺄": 631,
636
+ "뺏": 632,
637
+ "뺐": 633,
638
+ "뺨": 634,
639
+ "뺭": 635,
640
+ "뻐": 636,
641
+ "뻑": 637,
642
+ "뻔": 638,
643
+ "뻗": 639,
644
+ "뻘": 640,
645
+ "뻣": 641,
646
+ "뻥": 642,
647
+ "뼈": 643,
648
+ "뽀": 644,
649
+ "뽁": 645,
650
+ "뽑": 646,
651
+ "뽕": 647,
652
+ "뿌": 648,
653
+ "뿐": 649,
654
+ "뿔": 650,
655
+ "쁘": 651,
656
+ "쁜": 652,
657
+ "쁠": 653,
658
+ "쁨": 654,
659
+ "삐": 655,
660
+ "삥": 656,
661
+ "사": 657,
662
+ "삭": 658,
663
+ "산": 659,
664
+ "살": 660,
665
+ "삶": 661,
666
+ "삼": 662,
667
+ "삽": 663,
668
+ "삿": 664,
669
+ "샀": 665,
670
+ "상": 666,
671
+ "새": 667,
672
+ "색": 668,
673
+ "샌": 669,
674
+ "샐": 670,
675
+ "샘": 671,
676
+ "생": 672,
677
+ "샤": 673,
678
+ "샥": 674,
679
+ "샴": 675,
680
+ "샵": 676,
681
+ "샷": 677,
682
+ "서": 678,
683
+ "석": 679,
684
+ "섞": 680,
685
+ "선": 681,
686
+ "설": 682,
687
+ "섬": 683,
688
+ "섭": 684,
689
+ "섯": 685,
690
+ "섰": 686,
691
+ "성": 687,
692
+ "세": 688,
693
+ "센": 689,
694
+ "셀": 690,
695
+ "셈": 691,
696
+ "셉": 692,
697
+ "셋": 693,
698
+ "셌": 694,
699
+ "셔": 695,
700
+ "션": 696,
701
+ "셜": 697,
702
+ "셨": 698,
703
+ "소": 699,
704
+ "속": 700,
705
+ "손": 701,
706
+ "솔": 702,
707
+ "솜": 703,
708
+ "솟": 704,
709
+ "송": 705,
710
+ "솥": 706,
711
+ "쇄": 707,
712
+ "쇠": 708,
713
+ "쇼": 709,
714
+ "숀": 710,
715
+ "숍": 711,
716
+ "수": 712,
717
+ "숙": 713,
718
+ "순": 714,
719
+ "술": 715,
720
+ "숨": 716,
721
+ "숫": 717,
722
+ "숭": 718,
723
+ "숱": 719,
724
+ "숲": 720,
725
+ "숴": 721,
726
+ "쉐": 722,
727
+ "쉬": 723,
728
+ "쉴": 724,
729
+ "쉽": 725,
730
+ "슈": 726,
731
+ "슛": 727,
732
+ "스": 728,
733
+ "슨": 729,
734
+ "슬": 730,
735
+ "슴": 731,
736
+ "습": 732,
737
+ "슷": 733,
738
+ "승": 734,
739
+ "시": 735,
740
+ "식": 736,
741
+ "신": 737,
742
+ "싣": 738,
743
+ "실": 739,
744
+ "싫": 740,
745
+ "심": 741,
746
+ "십": 742,
747
+ "싴": 743,
748
+ "싶": 744,
749
+ "싸": 745,
750
+ "싹": 746,
751
+ "싼": 747,
752
+ "쌓": 748,
753
+ "쌤": 749,
754
+ "쌩": 750,
755
+ "쌰": 751,
756
+ "썜": 752,
757
+ "써": 753,
758
+ "썰": 754,
759
+ "썸": 755,
760
+ "썼": 756,
761
+ "쎄": 757,
762
+ "쏘": 758,
763
+ "쏙": 759,
764
+ "쏟": 760,
765
+ "쏠": 761,
766
+ "쐬": 762,
767
+ "쑥": 763,
768
+ "쓰": 764,
769
+ "쓱": 765,
770
+ "쓴": 766,
771
+ "쓸": 767,
772
+ "씀": 768,
773
+ "씁": 769,
774
+ "씌": 770,
775
+ "씨": 771,
776
+ "씩": 772,
777
+ "씬": 773,
778
+ "씹": 774,
779
+ "씻": 775,
780
+ "아": 776,
781
+ "악": 777,
782
+ "안": 778,
783
+ "앉": 779,
784
+ "않": 780,
785
+ "알": 781,
786
+ "앓": 782,
787
+ "암": 783,
788
+ "압": 784,
789
+ "앗": 785,
790
+ "았": 786,
791
+ "앙": 787,
792
+ "앞": 788,
793
+ "애": 789,
794
+ "액": 790,
795
+ "앤": 791,
796
+ "앨": 792,
797
+ "앰": 793,
798
+ "앴": 794,
799
+ "앵": 795,
800
+ "야": 796,
801
+ "약": 797,
802
+ "얀": 798,
803
+ "얇": 799,
804
+ "양": 800,
805
+ "얕": 801,
806
+ "얘": 802,
807
+ "얜": 803,
808
+ "어": 804,
809
+ "억": 805,
810
+ "언": 806,
811
+ "얹": 807,
812
+ "얻": 808,
813
+ "얼": 809,
814
+ "엄": 810,
815
+ "업": 811,
816
+ "없": 812,
817
+ "엇": 813,
818
+ "었": 814,
819
+ "엉": 815,
820
+ "엎": 816,
821
+ "에": 817,
822
+ "엑": 818,
823
+ "엔": 819,
824
+ "엘": 820,
825
+ "엠": 821,
826
+ "엣": 822,
827
+ "엥": 823,
828
+ "여": 824,
829
+ "역": 825,
830
+ "연": 826,
831
+ "열": 827,
832
+ "염": 828,
833
+ "엽": 829,
834
+ "엿": 830,
835
+ "였": 831,
836
+ "영": 832,
837
+ "옆": 833,
838
+ "예": 834,
839
+ "옛": 835,
840
+ "오": 836,
841
+ "옥": 837,
842
+ "온": 838,
843
+ "올": 839,
844
+ "옮": 840,
845
+ "옳": 841,
846
+ "옴": 842,
847
+ "옵": 843,
848
+ "옷": 844,
849
+ "옹": 845,
850
+ "와": 846,
851
+ "완": 847,
852
+ "왈": 848,
853
+ "왓": 849,
854
+ "왔": 850,
855
+ "왕": 851,
856
+ "왜": 852,
857
+ "왠": 853,
858
+ "외": 854,
859
+ "왼": 855,
860
+ "요": 856,
861
+ "욕": 857,
862
+ "용": 858,
863
+ "우": 859,
864
+ "욱": 860,
865
+ "운": 861,
866
+ "울": 862,
867
+ "움": 863,
868
+ "웁": 864,
869
+ "웃": 865,
870
+ "웅": 866,
871
+ "워": 867,
872
+ "원": 868,
873
+ "월": 869,
874
+ "웠": 870,
875
+ "웨": 871,
876
+ "웩": 872,
877
+ "웬": 873,
878
+ "웹": 874,
879
+ "위": 875,
880
+ "윈": 876,
881
+ "윗": 877,
882
+ "유": 878,
883
+ "육": 879,
884
+ "윤": 880,
885
+ "율": 881,
886
+ "융": 882,
887
+ "으": 883,
888
+ "윽": 884,
889
+ "은": 885,
890
+ "읃": 886,
891
+ "을": 887,
892
+ "음": 888,
893
+ "읍": 889,
894
+ "읏": 890,
895
+ "응": 891,
896
+ "의": 892,
897
+ "이": 893,
898
+ "익": 894,
899
+ "인": 895,
900
+ "일": 896,
901
+ "읽": 897,
902
+ "잃": 898,
903
+ "임": 899,
904
+ "입": 900,
905
+ "잇": 901,
906
+ "있": 902,
907
+ "잉": 903,
908
+ "잊": 904,
909
+ "자": 905,
910
+ "작": 906,
911
+ "잔": 907,
912
+ "잖": 908,
913
+ "잘": 909,
914
+ "잠": 910,
915
+ "잡": 911,
916
+ "잣": 912,
917
+ "장": 913,
918
+ "재": 914,
919
+ "잰": 915,
920
+ "잼": 916,
921
+ "잽": 917,
922
+ "쟁": 918,
923
+ "쟤": 919,
924
+ "저": 920,
925
+ "적": 921,
926
+ "전": 922,
927
+ "절": 923,
928
+ "젊": 924,
929
+ "점": 925,
930
+ "접": 926,
931
+ "정": 927,
932
+ "제": 928,
933
+ "젝": 929,
934
+ "젠": 930,
935
+ "젤": 931,
936
+ "져": 932,
937
+ "졌": 933,
938
+ "조": 934,
939
+ "족": 935,
940
+ "존": 936,
941
+ "졸": 937,
942
+ "좀": 938,
943
+ "좁": 939,
944
+ "종": 940,
945
+ "좋": 941,
946
+ "좌": 942,
947
+ "좔": 943,
948
+ "죄": 944,
949
+ "죠": 945,
950
+ "주": 946,
951
+ "죽": 947,
952
+ "준": 948,
953
+ "줄": 949,
954
+ "줌": 950,
955
+ "줍": 951,
956
+ "중": 952,
957
+ "줘": 953,
958
+ "줬": 954,
959
+ "쥐": 955,
960
+ "쥔": 956,
961
+ "쥬": 957,
962
+ "즈": 958,
963
+ "즉": 959,
964
+ "즌": 960,
965
+ "즐": 961,
966
+ "즘": 962,
967
+ "증": 963,
968
+ "지": 964,
969
+ "직": 965,
970
+ "진": 966,
971
+ "질": 967,
972
+ "짐": 968,
973
+ "집": 969,
974
+ "짓": 970,
975
+ "징": 971,
976
+ "짖": 972,
977
+ "짚": 973,
978
+ "짜": 974,
979
+ "짝": 975,
980
+ "짠": 976,
981
+ "짤": 977,
982
+ "짧": 978,
983
+ "짬": 979,
984
+ "짰": 980,
985
+ "짱": 981,
986
+ "째": 982,
987
+ "쨋": 983,
988
+ "쨌": 984,
989
+ "쩌": 985,
990
+ "쩍": 986,
991
+ "쩐": 987,
992
+ "쩔": 988,
993
+ "쩝": 989,
994
+ "쩠": 990,
995
+ "쪘": 991,
996
+ "쪼": 992,
997
+ "쪽": 993,
998
+ "쫀": 994,
999
+ "쫄": 995,
1000
+ "쫌": 996,
1001
+ "쫓": 997,
1002
+ "쫙": 998,
1003
+ "쭈": 999,
1004
+ "쭉": 1000,
1005
+ "쭤": 1001,
1006
+ "쮸": 1002,
1007
+ "쯤": 1003,
1008
+ "찌": 1004,
1009
+ "찍": 1005,
1010
+ "찐": 1006,
1011
+ "찔": 1007,
1012
+ "찜": 1008,
1013
+ "찝": 1009,
1014
+ "찡": 1010,
1015
+ "찢": 1011,
1016
+ "차": 1012,
1017
+ "착": 1013,
1018
+ "찬": 1014,
1019
+ "찮": 1015,
1020
+ "찰": 1016,
1021
+ "참": 1017,
1022
+ "찼": 1018,
1023
+ "창": 1019,
1024
+ "찾": 1020,
1025
+ "채": 1021,
1026
+ "책": 1022,
1027
+ "챌": 1023,
1028
+ "챕": 1024,
1029
+ "챙": 1025,
1030
+ "처": 1026,
1031
+ "척": 1027,
1032
+ "천": 1028,
1033
+ "철": 1029,
1034
+ "첨": 1030,
1035
+ "첩": 1031,
1036
+ "첫": 1032,
1037
+ "청": 1033,
1038
+ "체": 1034,
1039
+ "첼": 1035,
1040
+ "쳅": 1036,
1041
+ "쳐": 1037,
1042
+ "쳤": 1038,
1043
+ "초": 1039,
1044
+ "촉": 1040,
1045
+ "촌": 1041,
1046
+ "촘": 1042,
1047
+ "촛": 1043,
1048
+ "총": 1044,
1049
+ "촤": 1045,
1050
+ "촥": 1046,
1051
+ "촬": 1047,
1052
+ "최": 1048,
1053
+ "쵸": 1049,
1054
+ "추": 1050,
1055
+ "축": 1051,
1056
+ "춘": 1052,
1057
+ "출": 1053,
1058
+ "춤": 1054,
1059
+ "춥": 1055,
1060
+ "충": 1056,
1061
+ "춰": 1057,
1062
+ "췄": 1058,
1063
+ "췌": 1059,
1064
+ "취": 1060,
1065
+ "츠": 1061,
1066
+ "측": 1062,
1067
+ "층": 1063,
1068
+ "치": 1064,
1069
+ "칙": 1065,
1070
+ "친": 1066,
1071
+ "칠": 1067,
1072
+ "침": 1068,
1073
+ "칩": 1069,
1074
+ "칫": 1070,
1075
+ "칭": 1071,
1076
+ "카": 1072,
1077
+ "칵": 1073,
1078
+ "칸": 1074,
1079
+ "칼": 1075,
1080
+ "캉": 1076,
1081
+ "캐": 1077,
1082
+ "캔": 1078,
1083
+ "캘": 1079,
1084
+ "캠": 1080,
1085
+ "캣": 1081,
1086
+ "커": 1082,
1087
+ "컥": 1083,
1088
+ "컨": 1084,
1089
+ "컬": 1085,
1090
+ "컴": 1086,
1091
+ "컵": 1087,
1092
+ "컷": 1088,
1093
+ "컸": 1089,
1094
+ "케": 1090,
1095
+ "켓": 1091,
1096
+ "켜": 1092,
1097
+ "켰": 1093,
1098
+ "코": 1094,
1099
+ "콕": 1095,
1100
+ "콘": 1096,
1101
+ "콜": 1097,
1102
+ "콤": 1098,
1103
+ "콥": 1099,
1104
+ "콧": 1100,
1105
+ "콩": 1101,
1106
+ "콸": 1102,
1107
+ "쾌": 1103,
1108
+ "쿠": 1104,
1109
+ "쿤": 1105,
1110
+ "쿨": 1106,
1111
+ "퀄": 1107,
1112
+ "퀴": 1108,
1113
+ "큐": 1109,
1114
+ "큘": 1110,
1115
+ "크": 1111,
1116
+ "큰": 1112,
1117
+ "클": 1113,
1118
+ "큼": 1114,
1119
+ "큽": 1115,
1120
+ "키": 1116,
1121
+ "킨": 1117,
1122
+ "킬": 1118,
1123
+ "킴": 1119,
1124
+ "킵": 1120,
1125
+ "타": 1121,
1126
+ "탁": 1122,
1127
+ "탄": 1123,
1128
+ "탈": 1124,
1129
+ "탐": 1125,
1130
+ "탑": 1126,
1131
+ "탓": 1127,
1132
+ "탔": 1128,
1133
+ "탕": 1129,
1134
+ "태": 1130,
1135
+ "택": 1131,
1136
+ "탠": 1132,
1137
+ "탱": 1133,
1138
+ "터": 1134,
1139
+ "턱": 1135,
1140
+ "턴": 1136,
1141
+ "털": 1137,
1142
+ "텅": 1138,
1143
+ "테": 1139,
1144
+ "텍": 1140,
1145
+ "텐": 1141,
1146
+ "텔": 1142,
1147
+ "템": 1143,
1148
+ "텝": 1144,
1149
+ "토": 1145,
1150
+ "톡": 1146,
1151
+ "톤": 1147,
1152
+ "톨": 1148,
1153
+ "톱": 1149,
1154
+ "통": 1150,
1155
+ "퇴": 1151,
1156
+ "투": 1152,
1157
+ "툭": 1153,
1158
+ "툴": 1154,
1159
+ "툼": 1155,
1160
+ "튀": 1156,
1161
+ "튜": 1157,
1162
+ "트": 1158,
1163
+ "특": 1159,
1164
+ "튼": 1160,
1165
+ "틀": 1161,
1166
+ "틈": 1162,
1167
+ "틍": 1163,
1168
+ "티": 1164,
1169
+ "틱": 1165,
1170
+ "틴": 1166,
1171
+ "틸": 1167,
1172
+ "팀": 1168,
1173
+ "팁": 1169,
1174
+ "팅": 1170,
1175
+ "파": 1171,
1176
+ "팍": 1172,
1177
+ "팎": 1173,
1178
+ "판": 1174,
1179
+ "팔": 1175,
1180
+ "팜": 1176,
1181
+ "팠": 1177,
1182
+ "팥": 1178,
1183
+ "패": 1179,
1184
+ "팩": 1180,
1185
+ "팬": 1181,
1186
+ "팽": 1182,
1187
+ "퍼": 1183,
1188
+ "퍽": 1184,
1189
+ "펀": 1185,
1190
+ "펌": 1186,
1191
+ "페": 1187,
1192
+ "펙": 1188,
1193
+ "펜": 1189,
1194
+ "펠": 1190,
1195
+ "펩": 1191,
1196
+ "펴": 1192,
1197
+ "편": 1193,
1198
+ "펼": 1194,
1199
+ "폈": 1195,
1200
+ "평": 1196,
1201
+ "폐": 1197,
1202
+ "포": 1198,
1203
+ "폭": 1199,
1204
+ "폰": 1200,
1205
+ "폴": 1201,
1206
+ "폼": 1202,
1207
+ "표": 1203,
1208
+ "푸": 1204,
1209
+ "푹": 1205,
1210
+ "푼": 1206,
1211
+ "풀": 1207,
1212
+ "품": 1208,
1213
+ "풋": 1209,
1214
+ "풍": 1210,
1215
+ "퓨": 1211,
1216
+ "프": 1212,
1217
+ "픈": 1213,
1218
+ "플": 1214,
1219
+ "픔": 1215,
1220
+ "피": 1216,
1221
+ "핀": 1217,
1222
+ "필": 1218,
1223
+ "핌": 1219,
1224
+ "핍": 1220,
1225
+ "핑": 1221,
1226
+ "하": 1222,
1227
+ "학": 1223,
1228
+ "한": 1224,
1229
+ "할": 1225,
1230
+ "함": 1226,
1231
+ "합": 1227,
1232
+ "핫": 1228,
1233
+ "항": 1229,
1234
+ "해": 1230,
1235
+ "핵": 1231,
1236
+ "핸": 1232,
1237
+ "햅": 1233,
1238
+ "햇": 1234,
1239
+ "했": 1235,
1240
+ "행": 1236,
1241
+ "햍": 1237,
1242
+ "향": 1238,
1243
+ "헀": 1239,
1244
+ "허": 1240,
1245
+ "헉": 1241,
1246
+ "헌": 1242,
1247
+ "헐": 1243,
1248
+ "험": 1244,
1249
+ "헛": 1245,
1250
+ "헝": 1246,
1251
+ "헤": 1247,
1252
+ "헨": 1248,
1253
+ "헷": 1249,
1254
+ "헹": 1250,
1255
+ "혀": 1251,
1256
+ "혁": 1252,
1257
+ "현": 1253,
1258
+ "혈": 1254,
1259
+ "혐": 1255,
1260
+ "협": 1256,
1261
+ "혔": 1257,
1262
+ "형": 1258,
1263
+ "혜": 1259,
1264
+ "호": 1260,
1265
+ "혹": 1261,
1266
+ "혼": 1262,
1267
+ "홀": 1263,
1268
+ "홈": 1264,
1269
+ "홉": 1265,
1270
+ "홍": 1266,
1271
+ "화": 1267,
1272
+ "확": 1268,
1273
+ "환": 1269,
1274
+ "활": 1270,
1275
+ "황": 1271,
1276
+ "회": 1272,
1277
+ "획": 1273,
1278
+ "횟": 1274,
1279
+ "횡": 1275,
1280
+ "효": 1276,
1281
+ "후": 1277,
1282
+ "훈": 1278,
1283
+ "훌": 1279,
1284
+ "훑": 1280,
1285
+ "훨": 1281,
1286
+ "훼": 1282,
1287
+ "휘": 1283,
1288
+ "휙": 1284,
1289
+ "휩": 1285,
1290
+ "휴": 1286,
1291
+ "흉": 1287,
1292
+ "흐": 1288,
1293
+ "흑": 1289,
1294
+ "흔": 1290,
1295
+ "흘": 1291,
1296
+ "흙": 1292,
1297
+ "흠": 1293,
1298
+ "흡": 1294,
1299
+ "흥": 1295,
1300
+ "흩": 1296,
1301
+ "희": 1297,
1302
+ "흰": 1298,
1303
+ "히": 1299,
1304
+ "힌": 1300,
1305
+ "힐": 1301,
1306
+ "힘": 1302
1307
+ }