Upload folder using huggingface_hub

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- automatic-speech-recognition
+- ./sample_speech.py
+- generated_from_trainer
+model-index:
+- name: ko-xlsr5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ko-xlsr5
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.4067
+- Cer: 0.1077
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 1.4452        | 0.97  | 1800  | 0.9257          | 0.2337 |
+| 1.0684        | 1.95  | 3600  | 0.6873          | 0.1834 |
+| 0.9269        | 2.92  | 5400  | 0.5857          | 0.1599 |
+| 0.8264        | 3.9   | 7200  | 0.5357          | 0.1442 |
+| 0.7637        | 4.87  | 9000  | 0.5069          | 0.1365 |
+| 0.7033        | 5.85  | 10800 | 0.4744          | 0.1277 |
+| 0.652         | 6.82  | 12600 | 0.4477          | 0.1210 |
+| 0.5999        | 7.8   | 14400 | 0.4310          | 0.1144 |
+| 0.5606        | 8.77  | 16200 | 0.4150          | 0.1114 |
+| 0.5371        | 9.75  | 18000 | 0.4068          | 0.1085 |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 1761,
+  "<s>": 1760,
+  "[PAD]": 1759,
+  "[UNK]": 1758
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_cer": 0.1077281619824462,
+    "eval_loss": 0.4067296087741852,
+    "eval_runtime": 2073.6041,
+    "eval_samples": 14768,
+    "eval_samples_per_second": 7.122,
+    "eval_steps_per_second": 0.445,
+    "train_loss": 1.1888314855705748,
+    "train_runtime": 43297.9494,
+    "train_samples": 118190,
+    "train_samples_per_second": 27.297,
+    "train_steps_per_second": 0.426
+}

checkpoint-18000/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 1761,
+  "<s>": 1760,
+  "[PAD]": 1759,
+  "[UNK]": 1758
+}

checkpoint-18000/config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 1759,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 1762,
+  "xvector_output_dim": 512
+}

checkpoint-18000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee8cba8b87113afbad456378019467294b427eb53f50244845251f3c79f0a3c
+size 2504608182

checkpoint-18000/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-18000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8aa008f2e778812d341d185a3c44e9867dd5cc501cf27772fc51b7dfdf537d0
+size 1269126570

checkpoint-18000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90866d635c8f1eb9a83a3a92cf6a56257ec494ad6da2950dedbe88112fc5421
+size 15024

checkpoint-18000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ab40d20d388d4b3ce5682917ab192d36c19a1df4a08e09517291ca433fed3f
+size 15024

checkpoint-18000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea91ecc712d6ebd4089d02484d9ef8402424000f28fbe8bdb130875deafe9b8
+size 14960

checkpoint-18000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a0a57464f9f73c7ee12f92e842c2a9cd755816ac714b7e34d22c721408f726
+size 15024

checkpoint-18000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775f91634073dcbf980fb475a577a5136c844642dc116f272094aab6eaeda5e2
+size 1064

checkpoint-18000/special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

checkpoint-18000/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "1758": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1759": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1760": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1761": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "config": null,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
+  "tokenizer_type": "wav2vec2",
+  "trust_remote_code": false,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

checkpoint-18000/trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": 0.40675491094589233,
+  "best_model_checkpoint": "./ko-xlsr5/checkpoint-18000",
+  "epoch": 9.746852578854744,
+  "eval_steps": 1800,
+  "global_step": 18000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029839643652561246,
+      "loss": 11.754,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00028839086859688194,
+      "loss": 2.455,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00027836859688195985,
+      "loss": 1.4452,
+      "step": 1800
+    },
+    {
+      "epoch": 0.97,
+      "eval_cer": 0.23372905998439186,
+      "eval_loss": 0.9257286190986633,
+      "eval_runtime": 2065.8069,
+      "eval_samples_per_second": 7.149,
+      "eval_steps_per_second": 0.447,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002683630289532294,
+      "loss": 1.2319,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00025834075723830735,
+      "loss": 1.1229,
+      "step": 3000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002483184855233853,
+      "loss": 1.0684,
+      "step": 3600
+    },
+    {
+      "epoch": 1.95,
+      "eval_cer": 0.18344095102682245,
+      "eval_loss": 0.6873096227645874,
+      "eval_runtime": 2137.5713,
+      "eval_samples_per_second": 6.909,
+      "eval_steps_per_second": 0.432,
+      "step": 3600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002383129175946548,
+      "loss": 0.9894,
+      "step": 4200
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00022829064587973272,
+      "loss": 0.9499,
+      "step": 4800
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.00021826837416481068,
+      "loss": 0.9269,
+      "step": 5400
+    },
+    {
+      "epoch": 2.92,
+      "eval_cer": 0.15986839995296181,
+      "eval_loss": 0.5857065916061401,
+      "eval_runtime": 2062.0942,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.448,
+      "step": 5400
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.00020826280623608017,
+      "loss": 0.8687,
+      "step": 6000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0001982405345211581,
+      "loss": 0.856,
+      "step": 6600
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.00018821826280623606,
+      "loss": 0.8264,
+      "step": 7200
+    },
+    {
+      "epoch": 3.9,
+      "eval_cer": 0.14419078265145766,
+      "eval_loss": 0.5356672406196594,
+      "eval_runtime": 2072.5322,
+      "eval_samples_per_second": 7.126,
+      "eval_steps_per_second": 0.445,
+      "step": 7200
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.00017819599109131402,
+      "loss": 0.7946,
+      "step": 7800
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 0.00016819042316258353,
+      "loss": 0.781,
+      "step": 8400
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 0.00015816815144766144,
+      "loss": 0.7637,
+      "step": 9000
+    },
+    {
+      "epoch": 4.87,
+      "eval_cer": 0.1364936231171358,
+      "eval_loss": 0.5068702697753906,
+      "eval_runtime": 2140.8687,
+      "eval_samples_per_second": 6.898,
+      "eval_steps_per_second": 0.431,
+      "step": 9000
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.00014814587973273943,
+      "loss": 0.736,
+      "step": 9600
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 0.00013812360801781736,
+      "loss": 0.7097,
+      "step": 10200
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00012811804008908684,
+      "loss": 0.7033,
+      "step": 10800
+    },
+    {
+      "epoch": 5.85,
+      "eval_cer": 0.12771672314813826,
+      "eval_loss": 0.47439366579055786,
+      "eval_runtime": 2140.9721,
+      "eval_samples_per_second": 6.898,
+      "eval_steps_per_second": 0.431,
+      "step": 10800
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.0001180957683741648,
+      "loss": 0.6863,
+      "step": 11400
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00010807349665924275,
+      "loss": 0.6564,
+      "step": 12000
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 9.806792873051224e-05,
+      "loss": 0.652,
+      "step": 12600
+    },
+    {
+      "epoch": 6.82,
+      "eval_cer": 0.12095765493206187,
+      "eval_loss": 0.4477333426475525,
+      "eval_runtime": 2142.7063,
+      "eval_samples_per_second": 6.892,
+      "eval_steps_per_second": 0.431,
+      "step": 12600
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 8.804565701559018e-05,
+      "loss": 0.6258,
+      "step": 13200
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 7.802338530066816e-05,
+      "loss": 0.6085,
+      "step": 13800
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 6.801781737193764e-05,
+      "loss": 0.5999,
+      "step": 14400
+    },
+    {
+      "epoch": 7.8,
+      "eval_cer": 0.11436428945596049,
+      "eval_loss": 0.4309966564178467,
+      "eval_runtime": 2141.1385,
+      "eval_samples_per_second": 6.897,
+      "eval_steps_per_second": 0.431,
+      "step": 14400
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 5.799554565701558e-05,
+      "loss": 0.5889,
+      "step": 15000
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 4.798997772828508e-05,
+      "loss": 0.5754,
+      "step": 15600
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 3.7967706013363024e-05,
+      "loss": 0.5606,
+      "step": 16200
+    },
+    {
+      "epoch": 8.77,
+      "eval_cer": 0.11144845575736842,
+      "eval_loss": 0.41504111886024475,
+      "eval_runtime": 2070.5583,
+      "eval_samples_per_second": 7.132,
+      "eval_steps_per_second": 0.446,
+      "step": 16200
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 2.7945434298440978e-05,
+      "loss": 0.5528,
+      "step": 16800
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 1.792316258351893e-05,
+      "loss": 0.5452,
+      "step": 17400
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 7.917594654788419e-06,
+      "loss": 0.5371,
+      "step": 18000
+    },
+    {
+      "epoch": 9.75,
+      "eval_cer": 0.10851124106006992,
+      "eval_loss": 0.40675491094589233,
+      "eval_runtime": 2143.676,
+      "eval_samples_per_second": 6.889,
+      "eval_steps_per_second": 0.431,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 600,
+  "max_steps": 18460,
+  "num_train_epochs": 10,
+  "save_steps": 1800,
+  "total_flos": 1.2600418565012377e+20,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5991f05d83d1a9efa7459920af37d6d3825f48900d3736ade310f9ad9f5a092e
+size 4472

checkpoint-18000/vocab.json

@@ -0,0 +1,1762 @@
+{
+  "&": 1,
+  "0": 2,
+  "1": 3,
+  "2": 4,
+  "3": 5,
+  "4": 6,
+  "5": 7,
+  "6": 8,
+  "7": 9,
+  "8": 10,
+  "9": 11,
+  "[PAD]": 1759,
+  "[UNK]": 1758,
+  "a": 12,
+  "b": 13,
+  "c": 14,
+  "d": 15,
+  "e": 16,
+  "f": 17,
+  "g": 18,
+  "h": 19,
+  "i": 20,
+  "j": 21,
+  "k": 22,
+  "l": 23,
+  "m": 24,
+  "n": 25,
+  "o": 26,
+  "p": 27,
+  "q": 28,
+  "r": 29,
+  "s": 30,
+  "t": 31,
+  "u": 32,
+  "v": 33,
+  "w": 34,
+  "x": 35,
+  "y": 36,
+  "z": 37,
+  "|": 0,
+  "ㄴ": 38,
+  "ㅅ": 39,
+  "ㅋ": 40,
+  "ㅡ": 41,
+  "가": 42,
+  "각": 43,
+  "간": 44,
+  "갇": 45,
+  "갈": 46,
+  "감": 47,
+  "갑": 48,
+  "값": 49,
+  "갓": 50,
+  "갔": 51,
+  "강": 52,
+  "갖": 53,
+  "갗": 54,
+  "같": 55,
+  "갛": 56,
+  "개": 57,
+  "객": 58,
+  "갠": 59,
+  "갤": 60,
+  "갬": 61,
+  "갯": 62,
+  "갰": 63,
+  "갱": 64,
+  "갸": 65,
+  "걀": 66,
+  "걍": 67,
+  "걎": 68,
+  "걔": 69,
+  "걘": 70,
+  "거": 71,
+  "걱": 72,
+  "건": 73,
+  "걷": 74,
+  "걸": 75,
+  "검": 76,
+  "겁": 77,
+  "것": 78,
+  "겄": 79,
+  "겅": 80,
+  "겉": 81,
+  "겋": 82,
+  "게": 83,
+  "겐": 84,
+  "겔": 85,
+  "겜": 86,
+  "겟": 87,
+  "겠": 88,
+  "겨": 89,
+  "격": 90,
+  "겪": 91,
+  "견": 92,
+  "결": 93,
+  "겸": 94,
+  "겹": 95,
+  "겼": 96,
+  "경": 97,
+  "곁": 98,
+  "계": 99,
+  "곗": 100,
+  "곘": 101,
+  "고": 102,
+  "곡": 103,
+  "곤": 104,
+  "곧": 105,
+  "골": 106,
+  "곰": 107,
+  "곱": 108,
+  "곳": 109,
+  "공": 110,
+  "곶": 111,
+  "과": 112,
+  "곽": 113,
+  "관": 114,
+  "괄": 115,
+  "괌": 116,
+  "괍": 117,
+  "광": 118,
+  "괘": 119,
+  "괜": 120,
+  "괞": 121,
+  "괭": 122,
+  "괴": 123,
+  "굉": 124,
+  "교": 125,
+  "구": 126,
+  "국": 127,
+  "군": 128,
+  "굳": 129,
+  "굴": 130,
+  "굵": 131,
+  "굶": 132,
+  "굽": 133,
+  "굿": 134,
+  "궁": 135,
+  "궈": 136,
+  "권": 137,
+  "궐": 138,
+  "궜": 139,
+  "궤": 140,
+  "귀": 141,
+  "귄": 142,
+  "귓": 143,
+  "규": 144,
+  "균": 145,
+  "귤": 146,
+  "그": 147,
+  "극": 148,
+  "근": 149,
+  "귿": 150,
+  "글": 151,
+  "긁": 152,
+  "금": 153,
+  "급": 154,
+  "긋": 155,
+  "긍": 156,
+  "기": 157,
+  "긴": 158,
+  "길": 159,
+  "김": 160,
+  "깁": 161,
+  "깃": 162,
+  "깄": 163,
+  "깅": 164,
+  "깉": 165,
+  "깊": 166,
+  "까": 167,
+  "깍": 168,
+  "깎": 169,
+  "깐": 170,
+  "깔": 171,
+  "깜": 172,
+  "깝": 173,
+  "깠": 174,
+  "깡": 175,
+  "깥": 176,
+  "깨": 177,
+  "깬": 178,
+  "깰": 179,
+  "깹": 180,
+  "깻": 181,
+  "깼": 182,
+  "꺄": 183,
+  "꺼": 184,
+  "꺽": 185,
+  "꺾": 186,
+  "껀": 187,
+  "껄": 188,
+  "껌": 189,
+  "껍": 190,
+  "껏": 191,
+  "껐": 192,
+  "껑": 193,
+  "께": 194,
+  "껴": 195,
+  "꼈": 196,
+  "꼐": 197,
+  "꼬": 198,
+  "꼭": 199,
+  "꼰": 200,
+  "꼴": 201,
+  "꼼": 202,
+  "꼽": 203,
+  "꽁": 204,
+  "꽂": 205,
+  "꽃": 206,
+  "꽈": 207,
+  "꽉": 208,
+  "꽝": 209,
+  "꽤": 210,
+  "꽥": 211,
+  "꾜": 212,
+  "꾸": 213,
+  "꾹": 214,
+  "꾼": 215,
+  "꿀": 216,
+  "꿇": 217,
+  "꿈": 218,
+  "꿉": 219,
+  "꿋": 220,
+  "꿍": 221,
+  "꿔": 222,
+  "꿨": 223,
+  "꿩": 224,
+  "꿰": 225,
+  "뀌": 226,
+  "뀐": 227,
+  "뀔": 228,
+  "뀜": 229,
+  "뀝": 230,
+  "뀨": 231,
+  "끄": 232,
+  "끈": 233,
+  "끊": 234,
+  "끌": 235,
+  "끓": 236,
+  "끔": 237,
+  "끕": 238,
+  "끗": 239,
+  "끝": 240,
+  "끼": 241,
+  "끽": 242,
+  "낀": 243,
+  "낄": 244,
+  "낌": 245,
+  "낍": 246,
+  "낑": 247,
+  "나": 248,
+  "낙": 249,
+  "낚": 250,
+  "난": 251,
+  "날": 252,
+  "낡": 253,
+  "남": 254,
+  "납": 255,
+  "낫": 256,
+  "났": 257,
+  "낭": 258,
+  "낮": 259,
+  "낯": 260,
+  "낱": 261,
+  "낳": 262,
+  "내": 263,
+  "낵": 264,
+  "낸": 265,
+  "낼": 266,
+  "냄": 267,
+  "냅": 268,
+  "냇": 269,
+  "냈": 270,
+  "냉": 271,
+  "냐": 272,
+  "냠": 273,
+  "냥": 274,
+  "너": 275,
+  "넉": 276,
+  "넌": 277,
+  "널": 278,
+  "넓": 279,
+  "넘": 280,
+  "넙": 281,
+  "넛": 282,
+  "넢": 283,
+  "넣": 284,
+  "네": 285,
+  "넥": 286,
+  "넨": 287,
+  "넬": 288,
+  "넴": 289,
+  "넵": 290,
+  "넷": 291,
+  "넹": 292,
+  "녀": 293,
+  "녁": 294,
+  "년": 295,
+  "념": 296,
+  "녔": 297,
+  "녕": 298,
+  "녘": 299,
+  "녜": 300,
+  "노": 301,
+  "녹": 302,
+  "논": 303,
+  "놀": 304,
+  "놈": 305,
+  "놉": 306,
+  "농": 307,
+  "높": 308,
+  "놓": 309,
+  "놔": 310,
+  "놧": 311,
+  "놨": 312,
+  "놯": 313,
+  "뇌": 314,
+  "뇨": 315,
+  "뇽": 316,
+  "누": 317,
+  "눅": 318,
+  "눈": 319,
+  "눌": 320,
+  "눔": 321,
+  "눕": 322,
+  "눗": 323,
+  "눠": 324,
+  "눴": 325,
+  "뉘": 326,
+  "뉜": 327,
+  "뉠": 328,
+  "뉩": 329,
+  "뉴": 330,
+  "늄": 331,
+  "느": 332,
+  "늑": 333,
+  "는": 334,
+  "늗": 335,
+  "늘": 336,
+  "늙": 337,
+  "늠": 338,
+  "능": 339,
+  "늦": 340,
+  "늫": 341,
+  "늬": 342,
+  "니": 343,
+  "닉": 344,
+  "닌": 345,
+  "닐": 346,
+  "님": 347,
+  "닙": 348,
+  "닛": 349,
+  "닝": 350,
+  "다": 351,
+  "닥": 352,
+  "닦": 353,
+  "단": 354,
+  "닫": 355,
+  "달": 356,
+  "닭": 357,
+  "닮": 358,
+  "닳": 359,
+  "담": 360,
+  "답": 361,
+  "닷": 362,
+  "당": 363,
+  "닿": 364,
+  "대": 365,
+  "댁": 366,
+  "댄": 367,
+  "댈": 368,
+  "댐": 369,
+  "댑": 370,
+  "댓": 371,
+  "댔": 372,
+  "댕": 373,
+  "댗": 374,
+  "댜": 375,
+  "더": 376,
+  "덕": 377,
+  "던": 378,
+  "덜": 379,
+  "덟": 380,
+  "덤": 381,
+  "덥": 382,
+  "덧": 383,
+  "덩": 384,
+  "덮": 385,
+  "데": 386,
+  "덱": 387,
+  "덴": 388,
+  "델": 389,
+  "뎀": 390,
+  "뎁": 391,
+  "뎃": 392,
+  "뎅": 393,
+  "뎌": 394,
+  "도": 395,
+  "독": 396,
+  "돈": 397,
+  "돋": 398,
+  "돌": 399,
+  "돔": 400,
+  "돕": 401,
+  "돗": 402,
+  "동": 403,
+  "돼": 404,
+  "됐": 405,
+  "됑": 406,
+  "되": 407,
+  "된": 408,
+  "될": 409,
+  "됨": 410,
+  "됩": 411,
+  "두": 412,
+  "둑": 413,
+  "둔": 414,
+  "둘": 415,
+  "둠": 416,
+  "둡": 417,
+  "둣": 418,
+  "둥": 419,
+  "둬": 420,
+  "뒀": 421,
+  "뒤": 422,
+  "뒨": 423,
+  "뒷": 424,
+  "뒹": 425,
+  "듀": 426,
+  "듕": 427,
+  "드": 428,
+  "득": 429,
+  "든": 430,
+  "듣": 431,
+  "들": 432,
+  "듦": 433,
+  "듬": 434,
+  "듭": 435,
+  "듯": 436,
+  "등": 437,
+  "디": 438,
+  "딕": 439,
+  "딘": 440,
+  "딛": 441,
+  "딜": 442,
+  "딤": 443,
+  "딥": 444,
+  "딨": 445,
+  "딩": 446,
+  "딪": 447,
+  "따": 448,
+  "딱": 449,
+  "딴": 450,
+  "딸": 451,
+  "땀": 452,
+  "땁": 453,
+  "땃": 454,
+  "땄": 455,
+  "땅": 456,
+  "땋": 457,
+  "때": 458,
+  "땐": 459,
+  "땜": 460,
+  "땠": 461,
+  "땡": 462,
+  "떄": 463,
+  "떘": 464,
+  "떙": 465,
+  "떠": 466,
+  "떡": 467,
+  "떢": 468,
+  "떤": 469,
+  "떨": 470,
+  "떫": 471,
+  "떳": 472,
+  "떴": 473,
+  "떵": 474,
+  "떻": 475,
+  "떼": 476,
+  "뗄": 477,
+  "뗍": 478,
+  "뗐": 479,
+  "또": 480,
+  "똑": 481,
+  "똘": 482,
+  "똠": 483,
+  "똥": 484,
+  "뙤": 485,
+  "뚜": 486,
+  "뚝": 487,
+  "뚤": 488,
+  "뚫": 489,
+  "뚱": 490,
+  "뛰": 491,
+  "뛴": 492,
+  "뛸": 493,
+  "뜁": 494,
+  "뜨": 495,
+  "뜩": 496,
+  "뜬": 497,
+  "뜯": 498,
+  "뜰": 499,
+  "뜸": 500,
+  "뜹": 501,
+  "뜻": 502,
+  "뜽": 503,
+  "띄": 504,
+  "띈": 505,
+  "띌": 506,
+  "띕": 507,
+  "띠": 508,
+  "띡": 509,
+  "띨": 510,
+  "띱": 511,
+  "띵": 512,
+  "라": 513,
+  "락": 514,
+  "란": 515,
+  "랄": 516,
+  "람": 517,
+  "랍": 518,
+  "랏": 519,
+  "랐": 520,
+  "랑": 521,
+  "랖": 522,
+  "랗": 523,
+  "래": 524,
+  "랙": 525,
+  "랜": 526,
+  "랠": 527,
+  "램": 528,
+  "랩": 529,
+  "랫": 530,
+  "랬": 531,
+  "랭": 532,
+  "랴": 533,
+  "략": 534,
+  "랼": 535,
+  "량": 536,
+  "러": 537,
+  "럭": 538,
+  "런": 539,
+  "럴": 540,
+  "럼": 541,
+  "럽": 542,
+  "럿": 543,
+  "렀": 544,
+  "렁": 545,
+  "렇": 546,
+  "레": 547,
+  "렉": 548,
+  "렌": 549,
+  "렐": 550,
+  "렘": 551,
+  "렙": 552,
+  "렛": 553,
+  "렜": 554,
+  "려": 555,
+  "력": 556,
+  "련": 557,
+  "렬": 558,
+  "렴": 559,
+  "렵": 560,
+  "렷": 561,
+  "렸": 562,
+  "령": 563,
+  "렿": 564,
+  "례": 565,
+  "로": 566,
+  "록": 567,
+  "론": 568,
+  "롤": 569,
+  "롬": 570,
+  "롭": 571,
+  "롯": 572,
+  "롱": 573,
+  "롷": 574,
+  "롸": 575,
+  "뢰": 576,
+  "료": 577,
+  "룡": 578,
+  "루": 579,
+  "룩": 580,
+  "룰": 581,
+  "룸": 582,
+  "룹": 583,
+  "룽": 584,
+  "뤄": 585,
+  "뤘": 586,
+  "뤼": 587,
+  "륑": 588,
+  "류": 589,
+  "륙": 590,
+  "률": 591,
+  "륨": 592,
+  "륭": 593,
+  "르": 594,
+  "륵": 595,
+  "른": 596,
+  "를": 597,
+  "름": 598,
+  "릅": 599,
+  "릇": 600,
+  "릉": 601,
+  "릎": 602,
+  "릏": 603,
+  "리": 604,
+  "릭": 605,
+  "린": 606,
+  "릴": 607,
+  "림": 608,
+  "립": 609,
+  "릿": 610,
+  "링": 611,
+  "마": 612,
+  "막": 613,
+  "만": 614,
+  "맍": 615,
+  "많": 616,
+  "말": 617,
+  "맑": 618,
+  "맘": 619,
+  "맙": 620,
+  "맛": 621,
+  "맜": 622,
+  "망": 623,
+  "맞": 624,
+  "맡": 625,
+  "맣": 626,
+  "매": 627,
+  "맥": 628,
+  "맨": 629,
+  "맴": 630,
+  "맵": 631,
+  "맸": 632,
+  "맹": 633,
+  "맺": 634,
+  "머": 635,
+  "먹": 636,
+  "먼": 637,
+  "멀": 638,
+  "멈": 639,
+  "멉": 640,
+  "멋": 641,
+  "멍": 642,
+  "메": 643,
+  "멕": 644,
+  "멘": 645,
+  "멜": 646,
+  "멤": 647,
+  "멥": 648,
+  "멧": 649,
+  "멨": 650,
+  "멩": 651,
+  "며": 652,
+  "멱": 653,
+  "면": 654,
+  "멸": 655,
+  "명": 656,
+  "몇": 657,
+  "모": 658,
+  "목": 659,
+  "몫": 660,
+  "몬": 661,
+  "몰": 662,
+  "몸": 663,
+  "몹": 664,
+  "못": 665,
+  "몽": 666,
+  "묘": 667,
+  "묙": 668,
+  "무": 669,
+  "묵": 670,
+  "묶": 671,
+  "문": 672,
+  "묻": 673,
+  "물": 674,
+  "묽": 675,
+  "뭅": 676,
+  "뭇": 677,
+  "뭉": 678,
+  "뭐": 679,
+  "뭔": 680,
+  "뭘": 681,
+  "뭠": 682,
+  "뭡": 683,
+  "뭣": 684,
+  "뭰": 685,
+  "뮌": 686,
+  "뮤": 687,
+  "뮨": 688,
+  "뮬": 689,
+  "므": 690,
+  "믄": 691,
+  "믈": 692,
+  "믐": 693,
+  "미": 694,
+  "믹": 695,
+  "민": 696,
+  "믾": 697,
+  "믿": 698,
+  "밀": 699,
+  "밈": 700,
+  "밉": 701,
+  "밌": 702,
+  "밍": 703,
+  "및": 704,
+  "밑": 705,
+  "바": 706,
+  "박": 707,
+  "밖": 708,
+  "반": 709,
+  "받": 710,
+  "발": 711,
+  "밝": 712,
+  "밟": 713,
+  "밤": 714,
+  "밥": 715,
+  "밧": 716,
+  "방": 717,
+  "밭": 718,
+  "배": 719,
+  "백": 720,
+  "밴": 721,
+  "밸": 722,
+  "뱀": 723,
+  "뱃": 724,
+  "뱄": 725,
+  "뱅": 726,
+  "뱉": 727,
+  "뱌": 728,
+  "버": 729,
+  "벅": 730,
+  "번": 731,
+  "벌": 732,
+  "범": 733,
+  "법": 734,
+  "벗": 735,
+  "벙": 736,
+  "벚": 737,
+  "베": 738,
+  "벡": 739,
+  "벤": 740,
+  "벨": 741,
+  "벳": 742,
+  "벵": 743,
+  "벼": 744,
+  "벽": 745,
+  "변": 746,
+  "별": 747,
+  "볍": 748,
+  "볏": 749,
+  "볐": 750,
+  "병": 751,
+  "볕": 752,
+  "보": 753,
+  "복": 754,
+  "볶": 755,
+  "본": 756,
+  "볼": 757,
+  "봄": 758,
+  "봅": 759,
+  "봇": 760,
+  "봉": 761,
+  "봐": 762,
+  "봣": 763,
+  "봤": 764,
+  "봬": 765,
+  "봽": 766,
+  "뵀": 767,
+  "뵈": 768,
+  "뵌": 769,
+  "뵐": 770,
+  "뵙": 771,
+  "뵤": 772,
+  "뵬": 773,
+  "뵹": 774,
+  "부": 775,
+  "북": 776,
+  "분": 777,
+  "붇": 778,
+  "불": 779,
+  "붉": 780,
+  "붐": 781,
+  "붑": 782,
+  "붓": 783,
+  "붕": 784,
+  "붙": 785,
+  "붚": 786,
+  "뷔": 787,
+  "뷰": 788,
+  "브": 789,
+  "븐": 790,
+  "블": 791,
+  "븕": 792,
+  "븥": 793,
+  "비": 794,
+  "빅": 795,
+  "빈": 796,
+  "빋": 797,
+  "빌": 798,
+  "빔": 799,
+  "빕": 800,
+  "빗": 801,
+  "빙": 802,
+  "빛": 803,
+  "빠": 804,
+  "빡": 805,
+  "빨": 806,
+  "빰": 807,
+  "빳": 808,
+  "빴": 809,
+  "빵": 810,
+  "빼": 811,
+  "빽": 812,
+  "뺀": 813,
+  "뺄": 814,
+  "뺍": 815,
+  "뺏": 816,
+  "뺐": 817,
+  "뺑": 818,
+  "뺨": 819,
+  "뺴": 820,
+  "뺵": 821,
+  "뻇": 822,
+  "뻈": 823,
+  "뻐": 824,
+  "뻑": 825,
+  "뻔": 826,
+  "뻗": 827,
+  "뻘": 828,
+  "뻣": 829,
+  "뻤": 830,
+  "뻥": 831,
+  "뻬": 832,
+  "뼈": 833,
+  "뼉": 834,
+  "뽀": 835,
+  "뽁": 836,
+  "뽂": 837,
+  "뽈": 838,
+  "뽐": 839,
+  "뽑": 840,
+  "뽕": 841,
+  "뽜": 842,
+  "뾰": 843,
+  "뾱": 844,
+  "뿅": 845,
+  "뿌": 846,
+  "뿍": 847,
+  "뿐": 848,
+  "뿔": 849,
+  "뿜": 850,
+  "뿝": 851,
+  "뿡": 852,
+  "쁘": 853,
+  "쁜": 854,
+  "쁠": 855,
+  "쁨": 856,
+  "쁩": 857,
+  "삐": 858,
+  "삑": 859,
+  "삘": 860,
+  "삥": 861,
+  "사": 862,
+  "삭": 863,
+  "산": 864,
+  "살": 865,
+  "삶": 866,
+  "삼": 867,
+  "삽": 868,
+  "삿": 869,
+  "샀": 870,
+  "상": 871,
+  "샅": 872,
+  "새": 873,
+  "색": 874,
+  "샌": 875,
+  "샐": 876,
+  "샘": 877,
+  "샙": 878,
+  "샛": 879,
+  "샜": 880,
+  "생": 881,
+  "샤": 882,
+  "샥": 883,
+  "샬": 884,
+  "샴": 885,
+  "샵": 886,
+  "샷": 887,
+  "샹": 888,
+  "샾": 889,
+  "섀": 890,
+  "서": 891,
+  "석": 892,
+  "섞": 893,
+  "선": 894,
+  "설": 895,
+  "섬": 896,
+  "섭": 897,
+  "섯": 898,
+  "섰": 899,
+  "성": 900,
+  "세": 901,
+  "섹": 902,
+  "센": 903,
+  "셀": 904,
+  "셈": 905,
+  "셉": 906,
+  "셋": 907,
+  "셌": 908,
+  "셔": 909,
+  "션": 910,
+  "셜": 911,
+  "셨": 912,
+  "셩": 913,
+  "셰": 914,
+  "셴": 915,
+  "소": 916,
+  "속": 917,
+  "손": 918,
+  "솔": 919,
+  "솜": 920,
+  "솝": 921,
+  "솟": 922,
+  "송": 923,
+  "솥": 924,
+  "솩": 925,
+  "쇄": 926,
+  "쇠": 927,
+  "쇼": 928,
+  "쇽": 929,
+  "숍": 930,
+  "숏": 931,
+  "숑": 932,
+  "수": 933,
+  "숙": 934,
+  "순": 935,
+  "숟": 936,
+  "술": 937,
+  "숨": 938,
+  "숩": 939,
+  "숫": 940,
+  "숭": 941,
+  "숯": 942,
+  "숱": 943,
+  "숲": 944,
+  "숴": 945,
+  "쉐": 946,
+  "쉬": 947,
+  "쉭": 948,
+  "쉰": 949,
+  "쉴": 950,
+  "쉼": 951,
+  "쉽": 952,
+  "슈": 953,
+  "슉": 954,
+  "슐": 955,
+  "슘": 956,
+  "슛": 957,
+  "슝": 958,
+  "스": 959,
+  "슥": 960,
+  "슨": 961,
+  "슬": 962,
+  "슴": 963,
+  "습": 964,
+  "슷": 965,
+  "승": 966,
+  "시": 967,
+  "식": 968,
+  "신": 969,
+  "싣": 970,
+  "실": 971,
+  "싫": 972,
+  "심": 973,
+  "십": 974,
+  "싯": 975,
+  "싱": 976,
+  "싶": 977,
+  "싸": 978,
+  "싹": 979,
+  "싼": 980,
+  "쌀": 981,
+  "쌈": 982,
+  "쌉": 983,
+  "쌌": 984,
+  "쌍": 985,
+  "쌓": 986,
+  "쌔": 987,
+  "쌤": 988,
+  "쌥": 989,
+  "쌩": 990,
+  "쌰": 991,
+  "썝": 992,
+  "썡": 993,
+  "써": 994,
+  "썩": 995,
+  "썬": 996,
+  "썰": 997,
+  "썸": 998,
+  "썹": 999,
+  "썼": 1000,
+  "썽": 1001,
+  "쎄": 1002,
+  "쎈": 1003,
+  "쎌": 1004,
+  "쎕": 1005,
+  "쎗": 1006,
+  "쎘": 1007,
+  "쎼": 1008,
+  "쏘": 1009,
+  "쏙": 1010,
+  "쏜": 1011,
+  "쏟": 1012,
+  "쏠": 1013,
+  "쏩": 1014,
+  "쏭": 1015,
+  "쏴": 1016,
+  "쏵": 1017,
+  "쐈": 1018,
+  "쐐": 1019,
+  "쐬": 1020,
+  "쐴": 1021,
+  "쑝": 1022,
+  "쑤": 1023,
+  "쑥": 1024,
+  "쑨": 1025,
+  "쒔": 1026,
+  "쒜": 1027,
+  "쓕": 1028,
+  "쓰": 1029,
+  "쓱": 1030,
+  "쓴": 1031,
+  "쓸": 1032,
+  "씀": 1033,
+  "씁": 1034,
+  "씌": 1035,
+  "씨": 1036,
+  "씩": 1037,
+  "씬": 1038,
+  "씰": 1039,
+  "씸": 1040,
+  "씹": 1041,
+  "씻": 1042,
+  "씽": 1043,
+  "아": 1044,
+  "악": 1045,
+  "앆": 1046,
+  "안": 1047,
+  "앉": 1048,
+  "않": 1049,
+  "알": 1050,
+  "앓": 1051,
+  "암": 1052,
+  "압": 1053,
+  "앗": 1054,
+  "았": 1055,
+  "앙": 1056,
+  "앞": 1057,
+  "애": 1058,
+  "액": 1059,
+  "앤": 1060,
+  "앨": 1061,
+  "앰": 1062,
+  "앱": 1063,
+  "앴": 1064,
+  "앵": 1065,
+  "야": 1066,
+  "약": 1067,
+  "얀": 1068,
+  "얄": 1069,
+  "얇": 1070,
+  "얌": 1071,
+  "얍": 1072,
+  "얏": 1073,
+  "양": 1074,
+  "얓": 1075,
+  "얕": 1076,
+  "얗": 1077,
+  "얘": 1078,
+  "얜": 1079,
+  "얫": 1080,
+  "얬": 1081,
+  "어": 1082,
+  "억": 1083,
+  "언": 1084,
+  "얹": 1085,
+  "얻": 1086,
+  "얼": 1087,
+  "얽": 1088,
+  "엄": 1089,
+  "업": 1090,
+  "없": 1091,
+  "엇": 1092,
+  "었": 1093,
+  "엉": 1094,
+  "엊": 1095,
+  "엌": 1096,
+  "엎": 1097,
+  "에": 1098,
+  "엑": 1099,
+  "엔": 1100,
+  "엘": 1101,
+  "엠": 1102,
+  "엣": 1103,
+  "엥": 1104,
+  "여": 1105,
+  "역": 1106,
+  "엮": 1107,
+  "연": 1108,
+  "열": 1109,
+  "염": 1110,
+  "엽": 1111,
+  "엿": 1112,
+  "였": 1113,
+  "영": 1114,
+  "옅": 1115,
+  "옆": 1116,
+  "옇": 1117,
+  "예": 1118,
+  "옌": 1119,
+  "옐": 1120,
+  "옙": 1121,
+  "옛": 1122,
+  "오": 1123,
+  "옥": 1124,
+  "온": 1125,
+  "올": 1126,
+  "옮": 1127,
+  "옳": 1128,
+  "옴": 1129,
+  "옵": 1130,
+  "옷": 1131,
+  "옹": 1132,
+  "옻": 1133,
+  "와": 1134,
+  "완": 1135,
+  "왈": 1136,
+  "왐": 1137,
+  "왑": 1138,
+  "왓": 1139,
+  "왔": 1140,
+  "왕": 1141,
+  "왜": 1142,
+  "왠": 1143,
+  "외": 1144,
+  "왼": 1145,
+  "요": 1146,
+  "욕": 1147,
+  "욜": 1148,
+  "용": 1149,
+  "우": 1150,
+  "욱": 1151,
+  "운": 1152,
+  "울": 1153,
+  "움": 1154,
+  "웁": 1155,
+  "웃": 1156,
+  "웅": 1157,
+  "워": 1158,
+  "원": 1159,
+  "월": 1160,
+  "웜": 1161,
+  "웠": 1162,
+  "웨": 1163,
+  "웬": 1164,
+  "웰": 1165,
+  "웹": 1166,
+  "위": 1167,
+  "윅": 1168,
+  "윈": 1169,
+  "윌": 1170,
+  "윗": 1171,
+  "윙": 1172,
+  "유": 1173,
+  "육": 1174,
+  "윤": 1175,
+  "율": 1176,
+  "융": 1177,
+  "으": 1178,
+  "윽": 1179,
+  "은": 1180,
+  "을": 1181,
+  "읊": 1182,
+  "음": 1183,
+  "읍": 1184,
+  "읎": 1185,
+  "읏": 1186,
+  "응": 1187,
+  "읒": 1188,
+  "읔": 1189,
+  "의": 1190,
+  "이": 1191,
+  "익": 1192,
+  "인": 1193,
+  "일": 1194,
+  "읽": 1195,
+  "잃": 1196,
+  "임": 1197,
+  "입": 1198,
+  "잇": 1199,
+  "있": 1200,
+  "잉": 1201,
+  "잊": 1202,
+  "잌": 1203,
+  "잍": 1204,
+  "잎": 1205,
+  "자": 1206,
+  "작": 1207,
+  "잔": 1208,
+  "잖": 1209,
+  "잘": 1210,
+  "잠": 1211,
+  "잡": 1212,
+  "잣": 1213,
+  "잤": 1214,
+  "장": 1215,
+  "잦": 1216,
+  "재": 1217,
+  "잭": 1218,
+  "잴": 1219,
+  "잼": 1220,
+  "잽": 1221,
+  "잿": 1222,
+  "쟀": 1223,
+  "쟁": 1224,
+  "쟈": 1225,
+  "쟎": 1226,
+  "쟤": 1227,
+  "쟨": 1228,
+  "저": 1229,
+  "적": 1230,
+  "전": 1231,
+  "절": 1232,
+  "젊": 1233,
+  "점": 1234,
+  "접": 1235,
+  "젓": 1236,
+  "정": 1237,
+  "젖": 1238,
+  "제": 1239,
+  "젝": 1240,
+  "젠": 1241,
+  "젤": 1242,
+  "젯": 1243,
+  "젱": 1244,
+  "져": 1245,
+  "졌": 1246,
+  "조": 1247,
+  "족": 1248,
+  "존": 1249,
+  "졸": 1250,
+  "좀": 1251,
+  "좁": 1252,
+  "좃": 1253,
+  "종": 1254,
+  "좆": 1255,
+  "좋": 1256,
+  "좌": 1257,
+  "좍": 1258,
+  "좔": 1259,
+  "좟": 1260,
+  "죄": 1261,
+  "죌": 1262,
+  "죠": 1263,
+  "주": 1264,
+  "죽": 1265,
+  "준": 1266,
+  "줄": 1267,
+  "줌": 1268,
+  "줍": 1269,
+  "줏": 1270,
+  "중": 1271,
+  "줘": 1272,
+  "줬": 1273,
+  "쥐": 1274,
+  "쥔": 1275,
+  "쥡": 1276,
+  "쥬": 1277,
+  "쥴": 1278,
+  "즈": 1279,
+  "즉": 1280,
+  "즌": 1281,
+  "즐": 1282,
+  "즘": 1283,
+  "즙": 1284,
+  "증": 1285,
+  "지": 1286,
+  "직": 1287,
+  "진": 1288,
+  "짆": 1289,
+  "질": 1290,
+  "짐": 1291,
+  "집": 1292,
+  "짓": 1293,
+  "징": 1294,
+  "짖": 1295,
+  "짙": 1296,
+  "짚": 1297,
+  "짜": 1298,
+  "짝": 1299,
+  "짠": 1300,
+  "짢": 1301,
+  "짤": 1302,
+  "짧": 1303,
+  "짬": 1304,
+  "짭": 1305,
+  "짰": 1306,
+  "짱": 1307,
+  "째": 1308,
+  "짹": 1309,
+  "짼": 1310,
+  "쨈": 1311,
+  "쨋": 1312,
+  "쨌": 1313,
+  "쨍": 1314,
+  "쨔": 1315,
+  "쨰": 1316,
+  "쩄": 1317,
+  "쩌": 1318,
+  "쩍": 1319,
+  "쩐": 1320,
+  "쩔": 1321,
+  "쩜": 1322,
+  "쩝": 1323,
+  "쩡": 1324,
+  "쩨": 1325,
+  "쩰": 1326,
+  "쪄": 1327,
+  "쪌": 1328,
+  "쪘": 1329,
+  "쪼": 1330,
+  "쪽": 1331,
+  "쫀": 1332,
+  "쫄": 1333,
+  "쫌": 1334,
+  "쫍": 1335,
+  "쫑": 1336,
+  "쫓": 1337,
+  "쫘": 1338,
+  "쫙": 1339,
+  "쫜": 1340,
+  "쫠": 1341,
+  "쬐": 1342,
+  "쭈": 1343,
+  "쭉": 1344,
+  "쭌": 1345,
+  "쭐": 1346,
+  "쭤": 1347,
+  "쮸": 1348,
+  "쮹": 1349,
+  "쯔": 1350,
+  "쯜": 1351,
+  "쯤": 1352,
+  "쯧": 1353,
+  "쯩": 1354,
+  "찌": 1355,
+  "찍": 1356,
+  "찐": 1357,
+  "찔": 1358,
+  "찜": 1359,
+  "찝": 1360,
+  "찡": 1361,
+  "찢": 1362,
+  "차": 1363,
+  "착": 1364,
+  "찬": 1365,
+  "찮": 1366,
+  "찰": 1367,
+  "참": 1368,
+  "찹": 1369,
+  "찻": 1370,
+  "찼": 1371,
+  "창": 1372,
+  "찾": 1373,
+  "찿": 1374,
+  "채": 1375,
+  "책": 1376,
+  "챌": 1377,
+  "챔": 1378,
+  "챕": 1379,
+  "챗": 1380,
+  "챘": 1381,
+  "챙": 1382,
+  "챠": 1383,
+  "챦": 1384,
+  "처": 1385,
+  "척": 1386,
+  "천": 1387,
+  "철": 1388,
+  "첨": 1389,
+  "첩": 1390,
+  "첫": 1391,
+  "청": 1392,
+  "체": 1393,
+  "첵": 1394,
+  "첸": 1395,
+  "첼": 1396,
+  "쳐": 1397,
+  "쳘": 1398,
+  "쳣": 1399,
+  "쳤": 1400,
+  "초": 1401,
+  "촉": 1402,
+  "촌": 1403,
+  "촘": 1404,
+  "총": 1405,
+  "촤": 1406,
+  "촥": 1407,
+  "촬": 1408,
+  "최": 1409,
+  "쵸": 1410,
+  "추": 1411,
+  "축": 1412,
+  "춘": 1413,
+  "출": 1414,
+  "춤": 1415,
+  "춥": 1416,
+  "춧": 1417,
+  "충": 1418,
+  "춰": 1419,
+  "췄": 1420,
+  "췌": 1421,
+  "취": 1422,
+  "츄": 1423,
+  "츠": 1424,
+  "측": 1425,
+  "츤": 1426,
+  "츨": 1427,
+  "츰": 1428,
+  "층": 1429,
+  "츼": 1430,
+  "치": 1431,
+  "칙": 1432,
+  "친": 1433,
+  "칠": 1434,
+  "침": 1435,
+  "칩": 1436,
+  "칫": 1437,
+  "칭": 1438,
+  "카": 1439,
+  "칵": 1440,
+  "칸": 1441,
+  "칼": 1442,
+  "캄": 1443,
+  "캅": 1444,
+  "캉": 1445,
+  "캐": 1446,
+  "캑": 1447,
+  "캔": 1448,
+  "캘": 1449,
+  "캠": 1450,
+  "캡": 1451,
+  "캣": 1452,
+  "캬": 1453,
+  "커": 1454,
+  "컥": 1455,
+  "컨": 1456,
+  "컬": 1457,
+  "컴": 1458,
+  "컵": 1459,
+  "컷": 1460,
+  "컸": 1461,
+  "컹": 1462,
+  "케": 1463,
+  "켄": 1464,
+  "켈": 1465,
+  "켓": 1466,
+  "켜": 1467,
+  "켠": 1468,
+  "켤": 1469,
+  "켰": 1470,
+  "코": 1471,
+  "콕": 1472,
+  "콘": 1473,
+  "콜": 1474,
+  "콤": 1475,
+  "콥": 1476,
+  "콧": 1477,
+  "콩": 1478,
+  "콸": 1479,
+  "쾅": 1480,
+  "쾌": 1481,
+  "쿄": 1482,
+  "쿠": 1483,
+  "쿡": 1484,
+  "쿤": 1485,
+  "쿨": 1486,
+  "쿰": 1487,
+  "쿱": 1488,
+  "쿵": 1489,
+  "쿼": 1490,
+  "퀀": 1491,
+  "퀄": 1492,
+  "퀘": 1493,
+  "퀴": 1494,
+  "퀵": 1495,
+  "퀸": 1496,
+  "큐": 1497,
+  "큘": 1498,
+  "크": 1499,
+  "큰": 1500,
+  "클": 1501,
+  "큼": 1502,
+  "큽": 1503,
+  "킁": 1504,
+  "키": 1505,
+  "킥": 1506,
+  "킨": 1507,
+  "킬": 1508,
+  "킴": 1509,
+  "킵": 1510,
+  "킷": 1511,
+  "킹": 1512,
+  "타": 1513,
+  "탁": 1514,
+  "탄": 1515,
+  "탈": 1516,
+  "탐": 1517,
+  "탑": 1518,
+  "탓": 1519,
+  "탔": 1520,
+  "탕": 1521,
+  "태": 1522,
+  "택": 1523,
+  "탠": 1524,
+  "탬": 1525,
+  "탭": 1526,
+  "탯": 1527,
+  "탱": 1528,
+  "터": 1529,
+  "턱": 1530,
+  "턴": 1531,
+  "털": 1532,
+  "텀": 1533,
+  "텁": 1534,
+  "텃": 1535,
+  "텄": 1536,
+  "텅": 1537,
+  "테": 1538,
+  "텍": 1539,
+  "텐": 1540,
+  "텔": 1541,
+  "템": 1542,
+  "텝": 1543,
+  "텡": 1544,
+  "텨": 1545,
+  "텼": 1546,
+  "토": 1547,
+  "톡": 1548,
+  "톤": 1549,
+  "톨": 1550,
+  "톰": 1551,
+  "톱": 1552,
+  "통": 1553,
+  "퇴": 1554,
+  "투": 1555,
+  "툭": 1556,
+  "툰": 1557,
+  "툴": 1558,
+  "툼": 1559,
+  "퉁": 1560,
+  "퉈": 1561,
+  "퉜": 1562,
+  "퉤": 1563,
+  "튀": 1564,
+  "튄": 1565,
+  "튈": 1566,
+  "튕": 1567,
+  "튜": 1568,
+  "튤": 1569,
+  "트": 1570,
+  "특": 1571,
+  "튼": 1572,
+  "틀": 1573,
+  "틈": 1574,
+  "틉": 1575,
+  "티": 1576,
+  "틱": 1577,
+  "틴": 1578,
+  "틸": 1579,
+  "팀": 1580,
+  "팁": 1581,
+  "팅": 1582,
+  "파": 1583,
+  "팍": 1584,
+  "팎": 1585,
+  "판": 1586,
+  "팔": 1587,
+  "팜": 1588,
+  "팝": 1589,
+  "팟": 1590,
+  "팠": 1591,
+  "팡": 1592,
+  "팥": 1593,
+  "패": 1594,
+  "팩": 1595,
+  "팬": 1596,
+  "팸": 1597,
+  "팻": 1598,
+  "팽": 1599,
+  "퍄": 1600,
+  "퍼": 1601,
+  "퍽": 1602,
+  "펀": 1603,
+  "펄": 1604,
+  "펌": 1605,
+  "펐": 1606,
+  "펑": 1607,
+  "페": 1608,
+  "펙": 1609,
+  "펜": 1610,
+  "펠": 1611,
+  "펩": 1612,
+  "펫": 1613,
+  "펭": 1614,
+  "펴": 1615,
+  "편": 1616,
+  "펼": 1617,
+  "폇": 1618,
+  "폈": 1619,
+  "평": 1620,
+  "폐": 1621,
+  "포": 1622,
+  "폭": 1623,
+  "폰": 1624,
+  "폴": 1625,
+  "폼": 1626,
+  "폿": 1627,
+  "퐁": 1628,
+  "퐉": 1629,
+  "푀": 1630,
+  "표": 1631,
+  "푸": 1632,
+  "푹": 1633,
+  "푼": 1634,
+  "풀": 1635,
+  "품": 1636,
+  "풉": 1637,
+  "풋": 1638,
+  "풍": 1639,
+  "퓌": 1640,
+  "퓨": 1641,
+  "프": 1642,
+  "픈": 1643,
+  "플": 1644,
+  "픔": 1645,
+  "픕": 1646,
+  "피": 1647,
+  "픽": 1648,
+  "핀": 1649,
+  "필": 1650,
+  "핏": 1651,
+  "핑": 1652,
+  "하": 1653,
+  "학": 1654,
+  "한": 1655,
+  "할": 1656,
+  "핥": 1657,
+  "함": 1658,
+  "합": 1659,
+  "핫": 1660,
+  "항": 1661,
+  "핰": 1662,
+  "해": 1663,
+  "핵": 1664,
+  "핸": 1665,
+  "핼": 1666,
+  "햄": 1667,
+  "햅": 1668,
+  "햇": 1669,
+  "했": 1670,
+  "행": 1671,
+  "햠": 1672,
+  "향": 1673,
+  "허": 1674,
+  "헉": 1675,
+  "헌": 1676,
+  "헐": 1677,
+  "험": 1678,
+  "헛": 1679,
+  "헝": 1680,
+  "헤": 1681,
+  "헥": 1682,
+  "헨": 1683,
+  "헬": 1684,
+  "헴": 1685,
+  "헵": 1686,
+  "헷": 1687,
+  "헹": 1688,
+  "혀": 1689,
+  "혁": 1690,
+  "현": 1691,
+  "혈": 1692,
+  "혐": 1693,
+  "협": 1694,
+  "혓": 1695,
+  "혔": 1696,
+  "형": 1697,
+  "혜": 1698,
+  "호": 1699,
+  "혹": 1700,
+  "혼": 1701,
+  "홀": 1702,
+  "홈": 1703,
+  "홉": 1704,
+  "홋": 1705,
+  "홍": 1706,
+  "화": 1707,
+  "확": 1708,
+  "환": 1709,
+  "활": 1710,
+  "홥": 1711,
+  "황": 1712,
+  "회": 1713,
+  "획": 1714,
+  "횐": 1715,
+  "횟": 1716,
+  "횡": 1717,
+  "효": 1718,
+  "횩": 1719,
+  "후": 1720,
+  "훅": 1721,
+  "훈": 1722,
+  "훌": 1723,
+  "훑": 1724,
+  "훔": 1725,
+  "훕": 1726,
+  "훗": 1727,
+  "훠": 1728,
+  "훨": 1729,
+  "훼": 1730,
+  "휀": 1731,
+  "휑": 1732,
+  "휘": 1733,
+  "휙": 1734,
+  "휜": 1735,
+  "휠": 1736,
+  "휴": 1737,
+  "휸": 1738,
+  "흉": 1739,
+  "흐": 1740,
+  "흑": 1741,
+  "흔": 1742,
+  "흘": 1743,
+  "흙": 1744,
+  "흠": 1745,
+  "흡": 1746,
+  "흣": 1747,
+  "흥": 1748,
+  "흩": 1749,
+  "희": 1750,
+  "흰": 1751,
+  "히": 1752,
+  "힌": 1753,
+  "힐": 1754,
+  "힘": 1755,
+  "힙": 1756,
+  "힝": 1757
+}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 1759,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 1762,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_cer": 0.1077281619824462,
+    "eval_loss": 0.4067296087741852,
+    "eval_runtime": 2073.6041,
+    "eval_samples": 14768,
+    "eval_samples_per_second": 7.122,
+    "eval_steps_per_second": 0.445
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8aa008f2e778812d341d185a3c44e9867dd5cc501cf27772fc51b7dfdf537d0
+size 1269126570

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "1758": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1759": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1760": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1761": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "config": null,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
+  "tokenizer_type": "wav2vec2",
+  "trust_remote_code": false,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.1888314855705748,
+    "train_runtime": 43297.9494,
+    "train_samples": 118190,
+    "train_samples_per_second": 27.297,
+    "train_steps_per_second": 0.426
+}

trainer_state.json

@@ -0,0 +1,298 @@
+{
+  "best_metric": 0.40675491094589233,
+  "best_model_checkpoint": "./ko-xlsr5/checkpoint-18000",
+  "epoch": 9.995938811425477,
+  "eval_steps": 1800,
+  "global_step": 18460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029839643652561246,
+      "loss": 11.754,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00028839086859688194,
+      "loss": 2.455,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00027836859688195985,
+      "loss": 1.4452,
+      "step": 1800
+    },
+    {
+      "epoch": 0.97,
+      "eval_cer": 0.23372905998439186,
+      "eval_loss": 0.9257286190986633,
+      "eval_runtime": 2065.8069,
+      "eval_samples_per_second": 7.149,
+      "eval_steps_per_second": 0.447,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002683630289532294,
+      "loss": 1.2319,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00025834075723830735,
+      "loss": 1.1229,
+      "step": 3000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002483184855233853,
+      "loss": 1.0684,
+      "step": 3600
+    },
+    {
+      "epoch": 1.95,
+      "eval_cer": 0.18344095102682245,
+      "eval_loss": 0.6873096227645874,
+      "eval_runtime": 2137.5713,
+      "eval_samples_per_second": 6.909,
+      "eval_steps_per_second": 0.432,
+      "step": 3600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002383129175946548,
+      "loss": 0.9894,
+      "step": 4200
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00022829064587973272,
+      "loss": 0.9499,
+      "step": 4800
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.00021826837416481068,
+      "loss": 0.9269,
+      "step": 5400
+    },
+    {
+      "epoch": 2.92,
+      "eval_cer": 0.15986839995296181,
+      "eval_loss": 0.5857065916061401,
+      "eval_runtime": 2062.0942,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.448,
+      "step": 5400
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.00020826280623608017,
+      "loss": 0.8687,
+      "step": 6000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0001982405345211581,
+      "loss": 0.856,
+      "step": 6600
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.00018821826280623606,
+      "loss": 0.8264,
+      "step": 7200
+    },
+    {
+      "epoch": 3.9,
+      "eval_cer": 0.14419078265145766,
+      "eval_loss": 0.5356672406196594,
+      "eval_runtime": 2072.5322,
+      "eval_samples_per_second": 7.126,
+      "eval_steps_per_second": 0.445,
+      "step": 7200
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.00017819599109131402,
+      "loss": 0.7946,
+      "step": 7800
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 0.00016819042316258353,
+      "loss": 0.781,
+      "step": 8400
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 0.00015816815144766144,
+      "loss": 0.7637,
+      "step": 9000
+    },
+    {
+      "epoch": 4.87,
+      "eval_cer": 0.1364936231171358,
+      "eval_loss": 0.5068702697753906,
+      "eval_runtime": 2140.8687,
+      "eval_samples_per_second": 6.898,
+      "eval_steps_per_second": 0.431,
+      "step": 9000
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.00014814587973273943,
+      "loss": 0.736,
+      "step": 9600
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 0.00013812360801781736,
+      "loss": 0.7097,
+      "step": 10200
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00012811804008908684,
+      "loss": 0.7033,
+      "step": 10800
+    },
+    {
+      "epoch": 5.85,
+      "eval_cer": 0.12771672314813826,
+      "eval_loss": 0.47439366579055786,
+      "eval_runtime": 2140.9721,
+      "eval_samples_per_second": 6.898,
+      "eval_steps_per_second": 0.431,
+      "step": 10800
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.0001180957683741648,
+      "loss": 0.6863,
+      "step": 11400
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00010807349665924275,
+      "loss": 0.6564,
+      "step": 12000
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 9.806792873051224e-05,
+      "loss": 0.652,
+      "step": 12600
+    },
+    {
+      "epoch": 6.82,
+      "eval_cer": 0.12095765493206187,
+      "eval_loss": 0.4477333426475525,
+      "eval_runtime": 2142.7063,
+      "eval_samples_per_second": 6.892,
+      "eval_steps_per_second": 0.431,
+      "step": 12600
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 8.804565701559018e-05,
+      "loss": 0.6258,
+      "step": 13200
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 7.802338530066816e-05,
+      "loss": 0.6085,
+      "step": 13800
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 6.801781737193764e-05,
+      "loss": 0.5999,
+      "step": 14400
+    },
+    {
+      "epoch": 7.8,
+      "eval_cer": 0.11436428945596049,
+      "eval_loss": 0.4309966564178467,
+      "eval_runtime": 2141.1385,
+      "eval_samples_per_second": 6.897,
+      "eval_steps_per_second": 0.431,
+      "step": 14400
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 5.799554565701558e-05,
+      "loss": 0.5889,
+      "step": 15000
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 4.798997772828508e-05,
+      "loss": 0.5754,
+      "step": 15600
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 3.7967706013363024e-05,
+      "loss": 0.5606,
+      "step": 16200
+    },
+    {
+      "epoch": 8.77,
+      "eval_cer": 0.11144845575736842,
+      "eval_loss": 0.41504111886024475,
+      "eval_runtime": 2070.5583,
+      "eval_samples_per_second": 7.132,
+      "eval_steps_per_second": 0.446,
+      "step": 16200
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 2.7945434298440978e-05,
+      "loss": 0.5528,
+      "step": 16800
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 1.792316258351893e-05,
+      "loss": 0.5452,
+      "step": 17400
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 7.917594654788419e-06,
+      "loss": 0.5371,
+      "step": 18000
+    },
+    {
+      "epoch": 9.75,
+      "eval_cer": 0.10851124106006992,
+      "eval_loss": 0.40675491094589233,
+      "eval_runtime": 2143.676,
+      "eval_samples_per_second": 6.889,
+      "eval_steps_per_second": 0.431,
+      "step": 18000
+    },
+    {
+      "epoch": 10.0,
+      "step": 18460,
+      "total_flos": 1.2921277443498574e+20,
+      "train_loss": 1.1888314855705748,
+      "train_runtime": 43297.9494,
+      "train_samples_per_second": 27.297,
+      "train_steps_per_second": 0.426
+    }
+  ],
+  "logging_steps": 600,
+  "max_steps": 18460,
+  "num_train_epochs": 10,
+  "save_steps": 1800,
+  "total_flos": 1.2921277443498574e+20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5991f05d83d1a9efa7459920af37d6d3825f48900d3736ade310f9ad9f5a092e
+size 4472

vocab.json

@@ -0,0 +1,1762 @@
+{
+  "&": 1,
+  "0": 2,
+  "1": 3,
+  "2": 4,
+  "3": 5,
+  "4": 6,
+  "5": 7,
+  "6": 8,
+  "7": 9,
+  "8": 10,
+  "9": 11,
+  "[PAD]": 1759,
+  "[UNK]": 1758,
+  "a": 12,
+  "b": 13,
+  "c": 14,
+  "d": 15,
+  "e": 16,
+  "f": 17,
+  "g": 18,
+  "h": 19,
+  "i": 20,
+  "j": 21,
+  "k": 22,
+  "l": 23,
+  "m": 24,
+  "n": 25,
+  "o": 26,
+  "p": 27,
+  "q": 28,
+  "r": 29,
+  "s": 30,
+  "t": 31,
+  "u": 32,
+  "v": 33,
+  "w": 34,
+  "x": 35,
+  "y": 36,
+  "z": 37,
+  "|": 0,
+  "ㄴ": 38,
+  "ㅅ": 39,
+  "ㅋ": 40,
+  "ㅡ": 41,
+  "가": 42,
+  "각": 43,
+  "간": 44,
+  "갇": 45,
+  "갈": 46,
+  "감": 47,
+  "갑": 48,
+  "값": 49,
+  "갓": 50,
+  "갔": 51,
+  "강": 52,
+  "갖": 53,
+  "갗": 54,
+  "같": 55,
+  "갛": 56,
+  "개": 57,
+  "객": 58,
+  "갠": 59,
+  "갤": 60,
+  "갬": 61,
+  "갯": 62,
+  "갰": 63,
+  "갱": 64,
+  "갸": 65,
+  "걀": 66,
+  "걍": 67,
+  "걎": 68,
+  "걔": 69,
+  "걘": 70,
+  "거": 71,
+  "걱": 72,
+  "건": 73,
+  "걷": 74,
+  "걸": 75,
+  "검": 76,
+  "겁": 77,
+  "것": 78,
+  "겄": 79,
+  "겅": 80,
+  "겉": 81,
+  "겋": 82,
+  "게": 83,
+  "겐": 84,
+  "겔": 85,
+  "겜": 86,
+  "겟": 87,
+  "겠": 88,
+  "겨": 89,
+  "격": 90,
+  "겪": 91,
+  "견": 92,
+  "결": 93,
+  "겸": 94,
+  "겹": 95,
+  "겼": 96,
+  "경": 97,
+  "곁": 98,
+  "계": 99,
+  "곗": 100,
+  "곘": 101,
+  "고": 102,
+  "곡": 103,
+  "곤": 104,
+  "곧": 105,
+  "골": 106,
+  "곰": 107,
+  "곱": 108,
+  "곳": 109,
+  "공": 110,
+  "곶": 111,
+  "과": 112,
+  "곽": 113,
+  "관": 114,
+  "괄": 115,
+  "괌": 116,
+  "괍": 117,
+  "광": 118,
+  "괘": 119,
+  "괜": 120,
+  "괞": 121,
+  "괭": 122,
+  "괴": 123,
+  "굉": 124,
+  "교": 125,
+  "구": 126,
+  "국": 127,
+  "군": 128,
+  "굳": 129,
+  "굴": 130,
+  "굵": 131,
+  "굶": 132,
+  "굽": 133,
+  "굿": 134,
+  "궁": 135,
+  "궈": 136,
+  "권": 137,
+  "궐": 138,
+  "궜": 139,
+  "궤": 140,
+  "귀": 141,
+  "귄": 142,
+  "귓": 143,
+  "규": 144,
+  "균": 145,
+  "귤": 146,
+  "그": 147,
+  "극": 148,
+  "근": 149,
+  "귿": 150,
+  "글": 151,
+  "긁": 152,
+  "금": 153,
+  "급": 154,
+  "긋": 155,
+  "긍": 156,
+  "기": 157,
+  "긴": 158,
+  "길": 159,
+  "김": 160,
+  "깁": 161,
+  "깃": 162,
+  "깄": 163,
+  "깅": 164,
+  "깉": 165,
+  "깊": 166,
+  "까": 167,
+  "깍": 168,
+  "깎": 169,
+  "깐": 170,
+  "깔": 171,
+  "깜": 172,
+  "깝": 173,
+  "깠": 174,
+  "깡": 175,
+  "깥": 176,
+  "깨": 177,
+  "깬": 178,
+  "깰": 179,
+  "깹": 180,
+  "깻": 181,
+  "깼": 182,
+  "꺄": 183,
+  "꺼": 184,
+  "꺽": 185,
+  "꺾": 186,
+  "껀": 187,
+  "껄": 188,
+  "껌": 189,
+  "껍": 190,
+  "껏": 191,
+  "껐": 192,
+  "껑": 193,
+  "께": 194,
+  "껴": 195,
+  "꼈": 196,
+  "꼐": 197,
+  "꼬": 198,
+  "꼭": 199,
+  "꼰": 200,
+  "꼴": 201,
+  "꼼": 202,
+  "꼽": 203,
+  "꽁": 204,
+  "꽂": 205,
+  "꽃": 206,
+  "꽈": 207,
+  "꽉": 208,
+  "꽝": 209,
+  "꽤": 210,
+  "꽥": 211,
+  "꾜": 212,
+  "꾸": 213,
+  "꾹": 214,
+  "꾼": 215,
+  "꿀": 216,
+  "꿇": 217,
+  "꿈": 218,
+  "꿉": 219,
+  "꿋": 220,
+  "꿍": 221,
+  "꿔": 222,
+  "꿨": 223,
+  "꿩": 224,
+  "꿰": 225,
+  "뀌": 226,
+  "뀐": 227,
+  "뀔": 228,
+  "뀜": 229,
+  "뀝": 230,
+  "뀨": 231,
+  "끄": 232,
+  "끈": 233,
+  "끊": 234,
+  "끌": 235,
+  "끓": 236,
+  "끔": 237,
+  "끕": 238,
+  "끗": 239,
+  "끝": 240,
+  "끼": 241,
+  "끽": 242,
+  "낀": 243,
+  "낄": 244,
+  "낌": 245,
+  "낍": 246,
+  "낑": 247,
+  "나": 248,
+  "낙": 249,
+  "낚": 250,
+  "난": 251,
+  "날": 252,
+  "낡": 253,
+  "남": 254,
+  "납": 255,
+  "낫": 256,
+  "났": 257,
+  "낭": 258,
+  "낮": 259,
+  "낯": 260,
+  "낱": 261,
+  "낳": 262,
+  "내": 263,
+  "낵": 264,
+  "낸": 265,
+  "낼": 266,
+  "냄": 267,
+  "냅": 268,
+  "냇": 269,
+  "냈": 270,
+  "냉": 271,
+  "냐": 272,
+  "냠": 273,
+  "냥": 274,
+  "너": 275,
+  "넉": 276,
+  "넌": 277,
+  "널": 278,
+  "넓": 279,
+  "넘": 280,
+  "넙": 281,
+  "넛": 282,
+  "넢": 283,
+  "넣": 284,
+  "네": 285,
+  "넥": 286,
+  "넨": 287,
+  "넬": 288,
+  "넴": 289,
+  "넵": 290,
+  "넷": 291,
+  "넹": 292,
+  "녀": 293,
+  "녁": 294,
+  "년": 295,
+  "념": 296,
+  "녔": 297,
+  "녕": 298,
+  "녘": 299,
+  "녜": 300,
+  "노": 301,
+  "녹": 302,
+  "논": 303,
+  "놀": 304,
+  "놈": 305,
+  "놉": 306,
+  "농": 307,
+  "높": 308,
+  "놓": 309,
+  "놔": 310,
+  "놧": 311,
+  "놨": 312,
+  "놯": 313,
+  "뇌": 314,
+  "뇨": 315,
+  "뇽": 316,
+  "누": 317,
+  "눅": 318,
+  "눈": 319,
+  "눌": 320,
+  "눔": 321,
+  "눕": 322,
+  "눗": 323,
+  "눠": 324,
+  "눴": 325,
+  "뉘": 326,
+  "뉜": 327,
+  "뉠": 328,
+  "뉩": 329,
+  "뉴": 330,
+  "늄": 331,
+  "느": 332,
+  "늑": 333,
+  "는": 334,
+  "늗": 335,
+  "늘": 336,
+  "늙": 337,
+  "늠": 338,
+  "능": 339,
+  "늦": 340,
+  "늫": 341,
+  "늬": 342,
+  "니": 343,
+  "닉": 344,
+  "닌": 345,
+  "닐": 346,
+  "님": 347,
+  "닙": 348,
+  "닛": 349,
+  "닝": 350,
+  "다": 351,
+  "닥": 352,
+  "닦": 353,
+  "단": 354,
+  "닫": 355,
+  "달": 356,
+  "닭": 357,
+  "닮": 358,
+  "닳": 359,
+  "담": 360,
+  "답": 361,
+  "닷": 362,
+  "당": 363,
+  "닿": 364,
+  "대": 365,
+  "댁": 366,
+  "댄": 367,
+  "댈": 368,
+  "댐": 369,
+  "댑": 370,
+  "댓": 371,
+  "댔": 372,
+  "댕": 373,
+  "댗": 374,
+  "댜": 375,
+  "더": 376,
+  "덕": 377,
+  "던": 378,
+  "덜": 379,
+  "덟": 380,
+  "덤": 381,
+  "덥": 382,
+  "덧": 383,
+  "덩": 384,
+  "덮": 385,
+  "데": 386,
+  "덱": 387,
+  "덴": 388,
+  "델": 389,
+  "뎀": 390,
+  "뎁": 391,
+  "뎃": 392,
+  "뎅": 393,
+  "뎌": 394,
+  "도": 395,
+  "독": 396,
+  "돈": 397,
+  "돋": 398,
+  "돌": 399,
+  "돔": 400,
+  "돕": 401,
+  "돗": 402,
+  "동": 403,
+  "돼": 404,
+  "됐": 405,
+  "됑": 406,
+  "되": 407,
+  "된": 408,
+  "될": 409,
+  "됨": 410,
+  "됩": 411,
+  "두": 412,
+  "둑": 413,
+  "둔": 414,
+  "둘": 415,
+  "둠": 416,
+  "둡": 417,
+  "둣": 418,
+  "둥": 419,
+  "둬": 420,
+  "뒀": 421,
+  "뒤": 422,
+  "뒨": 423,
+  "뒷": 424,
+  "뒹": 425,
+  "듀": 426,
+  "듕": 427,
+  "드": 428,
+  "득": 429,
+  "든": 430,
+  "듣": 431,
+  "들": 432,
+  "듦": 433,
+  "듬": 434,
+  "듭": 435,
+  "듯": 436,
+  "등": 437,
+  "디": 438,
+  "딕": 439,
+  "딘": 440,
+  "딛": 441,
+  "딜": 442,
+  "딤": 443,
+  "딥": 444,
+  "딨": 445,
+  "딩": 446,
+  "딪": 447,
+  "따": 448,
+  "딱": 449,
+  "딴": 450,
+  "딸": 451,
+  "땀": 452,
+  "땁": 453,
+  "땃": 454,
+  "땄": 455,
+  "땅": 456,
+  "땋": 457,
+  "때": 458,
+  "땐": 459,
+  "땜": 460,
+  "땠": 461,
+  "땡": 462,
+  "떄": 463,
+  "떘": 464,
+  "떙": 465,
+  "떠": 466,
+  "떡": 467,
+  "떢": 468,
+  "떤": 469,
+  "떨": 470,
+  "떫": 471,
+  "떳": 472,
+  "떴": 473,
+  "떵": 474,
+  "떻": 475,
+  "떼": 476,
+  "뗄": 477,
+  "뗍": 478,
+  "뗐": 479,
+  "또": 480,
+  "똑": 481,
+  "똘": 482,
+  "똠": 483,
+  "똥": 484,
+  "뙤": 485,
+  "뚜": 486,
+  "뚝": 487,
+  "뚤": 488,
+  "뚫": 489,
+  "뚱": 490,
+  "뛰": 491,
+  "뛴": 492,
+  "뛸": 493,
+  "뜁": 494,
+  "뜨": 495,
+  "뜩": 496,
+  "뜬": 497,
+  "뜯": 498,
+  "뜰": 499,
+  "뜸": 500,
+  "뜹": 501,
+  "뜻": 502,
+  "뜽": 503,
+  "띄": 504,
+  "띈": 505,
+  "띌": 506,
+  "띕": 507,
+  "띠": 508,
+  "띡": 509,
+  "띨": 510,
+  "띱": 511,
+  "띵": 512,
+  "라": 513,
+  "락": 514,
+  "란": 515,
+  "랄": 516,
+  "람": 517,
+  "랍": 518,
+  "랏": 519,
+  "랐": 520,
+  "랑": 521,
+  "랖": 522,
+  "랗": 523,
+  "래": 524,
+  "랙": 525,
+  "랜": 526,
+  "랠": 527,
+  "램": 528,
+  "랩": 529,
+  "랫": 530,
+  "랬": 531,
+  "랭": 532,
+  "랴": 533,
+  "략": 534,
+  "랼": 535,
+  "량": 536,
+  "러": 537,
+  "럭": 538,
+  "런": 539,
+  "럴": 540,
+  "럼": 541,
+  "럽": 542,
+  "럿": 543,
+  "렀": 544,
+  "렁": 545,
+  "렇": 546,
+  "레": 547,
+  "렉": 548,
+  "렌": 549,
+  "렐": 550,
+  "렘": 551,
+  "렙": 552,
+  "렛": 553,
+  "렜": 554,
+  "려": 555,
+  "력": 556,
+  "련": 557,
+  "렬": 558,
+  "렴": 559,
+  "렵": 560,
+  "렷": 561,
+  "렸": 562,
+  "령": 563,
+  "렿": 564,
+  "례": 565,
+  "로": 566,
+  "록": 567,
+  "론": 568,
+  "롤": 569,
+  "롬": 570,
+  "롭": 571,
+  "롯": 572,
+  "롱": 573,
+  "롷": 574,
+  "롸": 575,
+  "뢰": 576,
+  "료": 577,
+  "룡": 578,
+  "루": 579,
+  "룩": 580,
+  "룰": 581,
+  "룸": 582,
+  "룹": 583,
+  "룽": 584,
+  "뤄": 585,
+  "뤘": 586,
+  "뤼": 587,
+  "륑": 588,
+  "류": 589,
+  "륙": 590,
+  "률": 591,
+  "륨": 592,
+  "륭": 593,
+  "르": 594,
+  "륵": 595,
+  "른": 596,
+  "를": 597,
+  "름": 598,
+  "릅": 599,
+  "릇": 600,
+  "릉": 601,
+  "릎": 602,
+  "릏": 603,
+  "리": 604,
+  "릭": 605,
+  "린": 606,
+  "릴": 607,
+  "림": 608,
+  "립": 609,
+  "릿": 610,
+  "링": 611,
+  "마": 612,
+  "막": 613,
+  "만": 614,
+  "맍": 615,
+  "많": 616,
+  "말": 617,
+  "맑": 618,
+  "맘": 619,
+  "맙": 620,
+  "맛": 621,
+  "맜": 622,
+  "망": 623,
+  "맞": 624,
+  "맡": 625,
+  "맣": 626,
+  "매": 627,
+  "맥": 628,
+  "맨": 629,
+  "맴": 630,
+  "맵": 631,
+  "맸": 632,
+  "맹": 633,
+  "맺": 634,
+  "머": 635,
+  "먹": 636,
+  "먼": 637,
+  "멀": 638,
+  "멈": 639,
+  "멉": 640,
+  "멋": 641,
+  "멍": 642,
+  "메": 643,
+  "멕": 644,
+  "멘": 645,
+  "멜": 646,
+  "멤": 647,
+  "멥": 648,
+  "멧": 649,
+  "멨": 650,
+  "멩": 651,
+  "며": 652,
+  "멱": 653,
+  "면": 654,
+  "멸": 655,
+  "명": 656,
+  "몇": 657,
+  "모": 658,
+  "목": 659,
+  "몫": 660,
+  "몬": 661,
+  "몰": 662,
+  "몸": 663,
+  "몹": 664,
+  "못": 665,
+  "몽": 666,
+  "묘": 667,
+  "묙": 668,
+  "무": 669,
+  "묵": 670,
+  "묶": 671,
+  "문": 672,
+  "묻": 673,
+  "물": 674,
+  "묽": 675,
+  "뭅": 676,
+  "뭇": 677,
+  "뭉": 678,
+  "뭐": 679,
+  "뭔": 680,
+  "뭘": 681,
+  "뭠": 682,
+  "뭡": 683,
+  "뭣": 684,
+  "뭰": 685,
+  "뮌": 686,
+  "뮤": 687,
+  "뮨": 688,
+  "뮬": 689,
+  "므": 690,
+  "믄": 691,
+  "믈": 692,
+  "믐": 693,
+  "미": 694,
+  "믹": 695,
+  "민": 696,
+  "믾": 697,
+  "믿": 698,
+  "밀": 699,
+  "밈": 700,
+  "밉": 701,
+  "밌": 702,
+  "밍": 703,
+  "및": 704,
+  "밑": 705,
+  "바": 706,
+  "박": 707,
+  "밖": 708,
+  "반": 709,
+  "받": 710,
+  "발": 711,
+  "밝": 712,
+  "밟": 713,
+  "밤": 714,
+  "밥": 715,
+  "밧": 716,
+  "방": 717,
+  "밭": 718,
+  "배": 719,
+  "백": 720,
+  "밴": 721,
+  "밸": 722,
+  "뱀": 723,
+  "뱃": 724,
+  "뱄": 725,
+  "뱅": 726,
+  "뱉": 727,
+  "뱌": 728,
+  "버": 729,
+  "벅": 730,
+  "번": 731,
+  "벌": 732,
+  "범": 733,
+  "법": 734,
+  "벗": 735,
+  "벙": 736,
+  "벚": 737,
+  "베": 738,
+  "벡": 739,
+  "벤": 740,
+  "벨": 741,
+  "벳": 742,
+  "벵": 743,
+  "벼": 744,
+  "벽": 745,
+  "변": 746,
+  "별": 747,
+  "볍": 748,
+  "볏": 749,
+  "볐": 750,
+  "병": 751,
+  "볕": 752,
+  "보": 753,
+  "복": 754,
+  "볶": 755,
+  "본": 756,
+  "볼": 757,
+  "봄": 758,
+  "봅": 759,
+  "봇": 760,
+  "봉": 761,
+  "봐": 762,
+  "봣": 763,
+  "봤": 764,
+  "봬": 765,
+  "봽": 766,
+  "뵀": 767,
+  "뵈": 768,
+  "뵌": 769,
+  "뵐": 770,
+  "뵙": 771,
+  "뵤": 772,
+  "뵬": 773,
+  "뵹": 774,
+  "부": 775,
+  "북": 776,
+  "분": 777,
+  "붇": 778,
+  "불": 779,
+  "붉": 780,
+  "붐": 781,
+  "붑": 782,
+  "붓": 783,
+  "붕": 784,
+  "붙": 785,
+  "붚": 786,
+  "뷔": 787,
+  "뷰": 788,
+  "브": 789,
+  "븐": 790,
+  "블": 791,
+  "븕": 792,
+  "븥": 793,
+  "비": 794,
+  "빅": 795,
+  "빈": 796,
+  "빋": 797,
+  "빌": 798,
+  "빔": 799,
+  "빕": 800,
+  "빗": 801,
+  "빙": 802,
+  "빛": 803,
+  "빠": 804,
+  "빡": 805,
+  "빨": 806,
+  "빰": 807,
+  "빳": 808,
+  "빴": 809,
+  "빵": 810,
+  "빼": 811,
+  "빽": 812,
+  "뺀": 813,
+  "뺄": 814,
+  "뺍": 815,
+  "뺏": 816,
+  "뺐": 817,
+  "뺑": 818,
+  "뺨": 819,
+  "뺴": 820,
+  "뺵": 821,
+  "뻇": 822,
+  "뻈": 823,
+  "뻐": 824,
+  "뻑": 825,
+  "뻔": 826,
+  "뻗": 827,
+  "뻘": 828,
+  "뻣": 829,
+  "뻤": 830,
+  "뻥": 831,
+  "뻬": 832,
+  "뼈": 833,
+  "뼉": 834,
+  "뽀": 835,
+  "뽁": 836,
+  "뽂": 837,
+  "뽈": 838,
+  "뽐": 839,
+  "뽑": 840,
+  "뽕": 841,
+  "뽜": 842,
+  "뾰": 843,
+  "뾱": 844,
+  "뿅": 845,
+  "뿌": 846,
+  "뿍": 847,
+  "뿐": 848,
+  "뿔": 849,
+  "뿜": 850,
+  "뿝": 851,
+  "뿡": 852,
+  "쁘": 853,
+  "쁜": 854,
+  "쁠": 855,
+  "쁨": 856,
+  "쁩": 857,
+  "삐": 858,
+  "삑": 859,
+  "삘": 860,
+  "삥": 861,
+  "사": 862,
+  "삭": 863,
+  "산": 864,
+  "살": 865,
+  "삶": 866,
+  "삼": 867,
+  "삽": 868,
+  "삿": 869,
+  "샀": 870,
+  "상": 871,
+  "샅": 872,
+  "새": 873,
+  "색": 874,
+  "샌": 875,
+  "샐": 876,
+  "샘": 877,
+  "샙": 878,
+  "샛": 879,
+  "샜": 880,
+  "생": 881,
+  "샤": 882,
+  "샥": 883,
+  "샬": 884,
+  "샴": 885,
+  "샵": 886,
+  "샷": 887,
+  "샹": 888,
+  "샾": 889,
+  "섀": 890,
+  "서": 891,
+  "석": 892,
+  "섞": 893,
+  "선": 894,
+  "설": 895,
+  "섬": 896,
+  "섭": 897,
+  "섯": 898,
+  "섰": 899,
+  "성": 900,
+  "세": 901,
+  "섹": 902,
+  "센": 903,
+  "셀": 904,
+  "셈": 905,
+  "셉": 906,
+  "셋": 907,
+  "셌": 908,
+  "셔": 909,
+  "션": 910,
+  "셜": 911,
+  "셨": 912,
+  "셩": 913,
+  "셰": 914,
+  "셴": 915,
+  "소": 916,
+  "속": 917,
+  "손": 918,
+  "솔": 919,
+  "솜": 920,
+  "솝": 921,
+  "솟": 922,
+  "송": 923,
+  "솥": 924,
+  "솩": 925,
+  "쇄": 926,
+  "쇠": 927,
+  "쇼": 928,
+  "쇽": 929,
+  "숍": 930,
+  "숏": 931,
+  "숑": 932,
+  "수": 933,
+  "숙": 934,
+  "순": 935,
+  "숟": 936,
+  "술": 937,
+  "숨": 938,
+  "숩": 939,
+  "숫": 940,
+  "숭": 941,
+  "숯": 942,
+  "숱": 943,
+  "숲": 944,
+  "숴": 945,
+  "쉐": 946,
+  "쉬": 947,
+  "쉭": 948,
+  "쉰": 949,
+  "쉴": 950,
+  "쉼": 951,
+  "쉽": 952,
+  "슈": 953,
+  "슉": 954,
+  "슐": 955,
+  "슘": 956,
+  "슛": 957,
+  "슝": 958,
+  "스": 959,
+  "슥": 960,
+  "슨": 961,
+  "슬": 962,
+  "슴": 963,
+  "습": 964,
+  "슷": 965,
+  "승": 966,
+  "시": 967,
+  "식": 968,
+  "신": 969,
+  "싣": 970,
+  "실": 971,
+  "싫": 972,
+  "심": 973,
+  "십": 974,
+  "싯": 975,
+  "싱": 976,
+  "싶": 977,
+  "싸": 978,
+  "싹": 979,
+  "싼": 980,
+  "쌀": 981,
+  "쌈": 982,
+  "쌉": 983,
+  "쌌": 984,
+  "쌍": 985,
+  "쌓": 986,
+  "쌔": 987,
+  "쌤": 988,
+  "쌥": 989,
+  "쌩": 990,
+  "쌰": 991,
+  "썝": 992,
+  "썡": 993,
+  "써": 994,
+  "썩": 995,
+  "썬": 996,
+  "썰": 997,
+  "썸": 998,
+  "썹": 999,
+  "썼": 1000,
+  "썽": 1001,
+  "쎄": 1002,
+  "쎈": 1003,
+  "쎌": 1004,
+  "쎕": 1005,
+  "쎗": 1006,
+  "쎘": 1007,
+  "쎼": 1008,
+  "쏘": 1009,
+  "쏙": 1010,
+  "쏜": 1011,
+  "쏟": 1012,
+  "쏠": 1013,
+  "쏩": 1014,
+  "쏭": 1015,
+  "쏴": 1016,
+  "쏵": 1017,
+  "쐈": 1018,
+  "쐐": 1019,
+  "쐬": 1020,
+  "쐴": 1021,
+  "쑝": 1022,
+  "쑤": 1023,
+  "쑥": 1024,
+  "쑨": 1025,
+  "쒔": 1026,
+  "쒜": 1027,
+  "쓕": 1028,
+  "쓰": 1029,
+  "쓱": 1030,
+  "쓴": 1031,
+  "쓸": 1032,
+  "씀": 1033,
+  "씁": 1034,
+  "씌": 1035,
+  "씨": 1036,
+  "씩": 1037,
+  "씬": 1038,
+  "씰": 1039,
+  "씸": 1040,
+  "씹": 1041,
+  "씻": 1042,
+  "씽": 1043,
+  "아": 1044,
+  "악": 1045,
+  "앆": 1046,
+  "안": 1047,
+  "앉": 1048,
+  "않": 1049,
+  "알": 1050,
+  "앓": 1051,
+  "암": 1052,
+  "압": 1053,
+  "앗": 1054,
+  "았": 1055,
+  "앙": 1056,
+  "앞": 1057,
+  "애": 1058,
+  "액": 1059,
+  "앤": 1060,
+  "앨": 1061,
+  "앰": 1062,
+  "앱": 1063,
+  "앴": 1064,
+  "앵": 1065,
+  "야": 1066,
+  "약": 1067,
+  "얀": 1068,
+  "얄": 1069,
+  "얇": 1070,
+  "얌": 1071,
+  "얍": 1072,
+  "얏": 1073,
+  "양": 1074,
+  "얓": 1075,
+  "얕": 1076,
+  "얗": 1077,
+  "얘": 1078,
+  "얜": 1079,
+  "얫": 1080,
+  "얬": 1081,
+  "어": 1082,
+  "억": 1083,
+  "언": 1084,
+  "얹": 1085,
+  "얻": 1086,
+  "얼": 1087,
+  "얽": 1088,
+  "엄": 1089,
+  "업": 1090,
+  "없": 1091,
+  "엇": 1092,
+  "었": 1093,
+  "엉": 1094,
+  "엊": 1095,
+  "엌": 1096,
+  "엎": 1097,
+  "에": 1098,
+  "엑": 1099,
+  "엔": 1100,
+  "엘": 1101,
+  "엠": 1102,
+  "엣": 1103,
+  "엥": 1104,
+  "여": 1105,
+  "역": 1106,
+  "엮": 1107,
+  "연": 1108,
+  "열": 1109,
+  "염": 1110,
+  "엽": 1111,
+  "엿": 1112,
+  "였": 1113,
+  "영": 1114,
+  "옅": 1115,
+  "옆": 1116,
+  "옇": 1117,
+  "예": 1118,
+  "옌": 1119,
+  "옐": 1120,
+  "옙": 1121,
+  "옛": 1122,
+  "오": 1123,
+  "옥": 1124,
+  "온": 1125,
+  "올": 1126,
+  "옮": 1127,
+  "옳": 1128,
+  "옴": 1129,
+  "옵": 1130,
+  "옷": 1131,
+  "옹": 1132,
+  "옻": 1133,
+  "와": 1134,
+  "완": 1135,
+  "왈": 1136,
+  "왐": 1137,
+  "왑": 1138,
+  "왓": 1139,
+  "왔": 1140,
+  "왕": 1141,
+  "왜": 1142,
+  "왠": 1143,
+  "외": 1144,
+  "왼": 1145,
+  "요": 1146,
+  "욕": 1147,
+  "욜": 1148,
+  "용": 1149,
+  "우": 1150,
+  "욱": 1151,
+  "운": 1152,
+  "울": 1153,
+  "움": 1154,
+  "웁": 1155,
+  "웃": 1156,
+  "웅": 1157,
+  "워": 1158,
+  "원": 1159,
+  "월": 1160,
+  "웜": 1161,
+  "웠": 1162,
+  "웨": 1163,
+  "웬": 1164,
+  "웰": 1165,
+  "웹": 1166,
+  "위": 1167,
+  "윅": 1168,
+  "윈": 1169,
+  "윌": 1170,
+  "윗": 1171,
+  "윙": 1172,
+  "유": 1173,
+  "육": 1174,
+  "윤": 1175,
+  "율": 1176,
+  "융": 1177,
+  "으": 1178,
+  "윽": 1179,
+  "은": 1180,
+  "을": 1181,
+  "읊": 1182,
+  "음": 1183,
+  "읍": 1184,
+  "읎": 1185,
+  "읏": 1186,
+  "응": 1187,
+  "읒": 1188,
+  "읔": 1189,
+  "의": 1190,
+  "이": 1191,
+  "익": 1192,
+  "인": 1193,
+  "일": 1194,
+  "읽": 1195,
+  "잃": 1196,
+  "임": 1197,
+  "입": 1198,
+  "잇": 1199,
+  "있": 1200,
+  "잉": 1201,
+  "잊": 1202,
+  "잌": 1203,
+  "잍": 1204,
+  "잎": 1205,
+  "자": 1206,
+  "작": 1207,
+  "잔": 1208,
+  "잖": 1209,
+  "잘": 1210,
+  "잠": 1211,
+  "잡": 1212,
+  "잣": 1213,
+  "잤": 1214,
+  "장": 1215,
+  "잦": 1216,
+  "재": 1217,
+  "잭": 1218,
+  "잴": 1219,
+  "잼": 1220,
+  "잽": 1221,
+  "잿": 1222,
+  "쟀": 1223,
+  "쟁": 1224,
+  "쟈": 1225,
+  "쟎": 1226,
+  "쟤": 1227,
+  "쟨": 1228,
+  "저": 1229,
+  "적": 1230,
+  "전": 1231,
+  "절": 1232,
+  "젊": 1233,
+  "점": 1234,
+  "접": 1235,
+  "젓": 1236,
+  "정": 1237,
+  "젖": 1238,
+  "제": 1239,
+  "젝": 1240,
+  "젠": 1241,
+  "젤": 1242,
+  "젯": 1243,
+  "젱": 1244,
+  "져": 1245,
+  "졌": 1246,
+  "조": 1247,
+  "족": 1248,
+  "존": 1249,
+  "졸": 1250,
+  "좀": 1251,
+  "좁": 1252,
+  "좃": 1253,
+  "종": 1254,
+  "좆": 1255,
+  "좋": 1256,
+  "좌": 1257,
+  "좍": 1258,
+  "좔": 1259,
+  "좟": 1260,
+  "죄": 1261,
+  "죌": 1262,
+  "죠": 1263,
+  "주": 1264,
+  "죽": 1265,
+  "준": 1266,
+  "줄": 1267,
+  "줌": 1268,
+  "줍": 1269,
+  "줏": 1270,
+  "중": 1271,
+  "줘": 1272,
+  "줬": 1273,
+  "쥐": 1274,
+  "쥔": 1275,
+  "쥡": 1276,
+  "쥬": 1277,
+  "쥴": 1278,
+  "즈": 1279,
+  "즉": 1280,
+  "즌": 1281,
+  "즐": 1282,
+  "즘": 1283,
+  "즙": 1284,
+  "증": 1285,
+  "지": 1286,
+  "직": 1287,
+  "진": 1288,
+  "짆": 1289,
+  "질": 1290,
+  "짐": 1291,
+  "집": 1292,
+  "짓": 1293,
+  "징": 1294,
+  "짖": 1295,
+  "짙": 1296,
+  "짚": 1297,
+  "짜": 1298,
+  "짝": 1299,
+  "짠": 1300,
+  "짢": 1301,
+  "짤": 1302,
+  "짧": 1303,
+  "짬": 1304,
+  "짭": 1305,
+  "짰": 1306,
+  "짱": 1307,
+  "째": 1308,
+  "짹": 1309,
+  "짼": 1310,
+  "쨈": 1311,
+  "쨋": 1312,
+  "쨌": 1313,
+  "쨍": 1314,
+  "쨔": 1315,
+  "쨰": 1316,
+  "쩄": 1317,
+  "쩌": 1318,
+  "쩍": 1319,
+  "쩐": 1320,
+  "쩔": 1321,
+  "쩜": 1322,
+  "쩝": 1323,
+  "쩡": 1324,
+  "쩨": 1325,
+  "쩰": 1326,
+  "쪄": 1327,
+  "쪌": 1328,
+  "쪘": 1329,
+  "쪼": 1330,
+  "쪽": 1331,
+  "쫀": 1332,
+  "쫄": 1333,
+  "쫌": 1334,
+  "쫍": 1335,
+  "쫑": 1336,
+  "쫓": 1337,
+  "쫘": 1338,
+  "쫙": 1339,
+  "쫜": 1340,
+  "쫠": 1341,
+  "쬐": 1342,
+  "쭈": 1343,
+  "쭉": 1344,
+  "쭌": 1345,
+  "쭐": 1346,
+  "쭤": 1347,
+  "쮸": 1348,
+  "쮹": 1349,
+  "쯔": 1350,
+  "쯜": 1351,
+  "쯤": 1352,
+  "쯧": 1353,
+  "쯩": 1354,
+  "찌": 1355,
+  "찍": 1356,
+  "찐": 1357,
+  "찔": 1358,
+  "찜": 1359,
+  "찝": 1360,
+  "찡": 1361,
+  "찢": 1362,
+  "차": 1363,
+  "착": 1364,
+  "찬": 1365,
+  "찮": 1366,
+  "찰": 1367,
+  "참": 1368,
+  "찹": 1369,
+  "찻": 1370,
+  "찼": 1371,
+  "창": 1372,
+  "찾": 1373,
+  "찿": 1374,
+  "채": 1375,
+  "책": 1376,
+  "챌": 1377,
+  "챔": 1378,
+  "챕": 1379,
+  "챗": 1380,
+  "챘": 1381,
+  "챙": 1382,
+  "챠": 1383,
+  "챦": 1384,
+  "처": 1385,
+  "척": 1386,
+  "천": 1387,
+  "철": 1388,
+  "첨": 1389,
+  "첩": 1390,
+  "첫": 1391,
+  "청": 1392,
+  "체": 1393,
+  "첵": 1394,
+  "첸": 1395,
+  "첼": 1396,
+  "쳐": 1397,
+  "쳘": 1398,
+  "쳣": 1399,
+  "쳤": 1400,
+  "초": 1401,
+  "촉": 1402,
+  "촌": 1403,
+  "촘": 1404,
+  "총": 1405,
+  "촤": 1406,
+  "촥": 1407,
+  "촬": 1408,
+  "최": 1409,
+  "쵸": 1410,
+  "추": 1411,
+  "축": 1412,
+  "춘": 1413,
+  "출": 1414,
+  "춤": 1415,
+  "춥": 1416,
+  "춧": 1417,
+  "충": 1418,
+  "춰": 1419,
+  "췄": 1420,
+  "췌": 1421,
+  "취": 1422,
+  "츄": 1423,
+  "츠": 1424,
+  "측": 1425,
+  "츤": 1426,
+  "츨": 1427,
+  "츰": 1428,
+  "층": 1429,
+  "츼": 1430,
+  "치": 1431,
+  "칙": 1432,
+  "친": 1433,
+  "칠": 1434,
+  "침": 1435,
+  "칩": 1436,
+  "칫": 1437,
+  "칭": 1438,
+  "카": 1439,
+  "칵": 1440,
+  "칸": 1441,
+  "칼": 1442,
+  "캄": 1443,
+  "캅": 1444,
+  "캉": 1445,
+  "캐": 1446,
+  "캑": 1447,
+  "캔": 1448,
+  "캘": 1449,
+  "캠": 1450,
+  "캡": 1451,
+  "캣": 1452,
+  "캬": 1453,
+  "커": 1454,
+  "컥": 1455,
+  "컨": 1456,
+  "컬": 1457,
+  "컴": 1458,
+  "컵": 1459,
+  "컷": 1460,
+  "컸": 1461,
+  "컹": 1462,
+  "케": 1463,
+  "켄": 1464,
+  "켈": 1465,
+  "켓": 1466,
+  "켜": 1467,
+  "켠": 1468,
+  "켤": 1469,
+  "켰": 1470,
+  "코": 1471,
+  "콕": 1472,
+  "콘": 1473,
+  "콜": 1474,
+  "콤": 1475,
+  "콥": 1476,
+  "콧": 1477,
+  "콩": 1478,
+  "콸": 1479,
+  "쾅": 1480,
+  "쾌": 1481,
+  "쿄": 1482,
+  "쿠": 1483,
+  "쿡": 1484,
+  "쿤": 1485,
+  "쿨": 1486,
+  "쿰": 1487,
+  "쿱": 1488,
+  "쿵": 1489,
+  "쿼": 1490,
+  "퀀": 1491,
+  "퀄": 1492,
+  "퀘": 1493,
+  "퀴": 1494,
+  "퀵": 1495,
+  "퀸": 1496,
+  "큐": 1497,
+  "큘": 1498,
+  "크": 1499,
+  "큰": 1500,
+  "클": 1501,
+  "큼": 1502,
+  "큽": 1503,
+  "킁": 1504,
+  "키": 1505,
+  "킥": 1506,
+  "킨": 1507,
+  "킬": 1508,
+  "킴": 1509,
+  "킵": 1510,
+  "킷": 1511,
+  "킹": 1512,
+  "타": 1513,
+  "탁": 1514,
+  "탄": 1515,
+  "탈": 1516,
+  "탐": 1517,
+  "탑": 1518,
+  "탓": 1519,
+  "탔": 1520,
+  "탕": 1521,
+  "태": 1522,
+  "택": 1523,
+  "탠": 1524,
+  "탬": 1525,
+  "탭": 1526,
+  "탯": 1527,
+  "탱": 1528,
+  "터": 1529,
+  "턱": 1530,
+  "턴": 1531,
+  "털": 1532,
+  "텀": 1533,
+  "텁": 1534,
+  "텃": 1535,
+  "텄": 1536,
+  "텅": 1537,
+  "테": 1538,
+  "텍": 1539,
+  "텐": 1540,
+  "텔": 1541,
+  "템": 1542,
+  "텝": 1543,
+  "텡": 1544,
+  "텨": 1545,
+  "텼": 1546,
+  "토": 1547,
+  "톡": 1548,
+  "톤": 1549,
+  "톨": 1550,
+  "톰": 1551,
+  "톱": 1552,
+  "통": 1553,
+  "퇴": 1554,
+  "투": 1555,
+  "툭": 1556,
+  "툰": 1557,
+  "툴": 1558,
+  "툼": 1559,
+  "퉁": 1560,
+  "퉈": 1561,
+  "퉜": 1562,
+  "퉤": 1563,
+  "튀": 1564,
+  "튄": 1565,
+  "튈": 1566,
+  "튕": 1567,
+  "튜": 1568,
+  "튤": 1569,
+  "트": 1570,
+  "특": 1571,
+  "튼": 1572,
+  "틀": 1573,
+  "틈": 1574,
+  "틉": 1575,
+  "티": 1576,
+  "틱": 1577,
+  "틴": 1578,
+  "틸": 1579,
+  "팀": 1580,
+  "팁": 1581,
+  "팅": 1582,
+  "파": 1583,
+  "팍": 1584,
+  "팎": 1585,
+  "판": 1586,
+  "팔": 1587,
+  "팜": 1588,
+  "팝": 1589,
+  "팟": 1590,
+  "팠": 1591,
+  "팡": 1592,
+  "팥": 1593,
+  "패": 1594,
+  "팩": 1595,
+  "팬": 1596,
+  "팸": 1597,
+  "팻": 1598,
+  "팽": 1599,
+  "퍄": 1600,
+  "퍼": 1601,
+  "퍽": 1602,
+  "펀": 1603,
+  "펄": 1604,
+  "펌": 1605,
+  "펐": 1606,
+  "펑": 1607,
+  "페": 1608,
+  "펙": 1609,
+  "펜": 1610,
+  "펠": 1611,
+  "펩": 1612,
+  "펫": 1613,
+  "펭": 1614,
+  "펴": 1615,
+  "편": 1616,
+  "펼": 1617,
+  "폇": 1618,
+  "폈": 1619,
+  "평": 1620,
+  "폐": 1621,
+  "포": 1622,
+  "폭": 1623,
+  "폰": 1624,
+  "폴": 1625,
+  "폼": 1626,
+  "폿": 1627,
+  "퐁": 1628,
+  "퐉": 1629,
+  "푀": 1630,
+  "표": 1631,
+  "푸": 1632,
+  "푹": 1633,
+  "푼": 1634,
+  "풀": 1635,
+  "품": 1636,
+  "풉": 1637,
+  "풋": 1638,
+  "풍": 1639,
+  "퓌": 1640,
+  "퓨": 1641,
+  "프": 1642,
+  "픈": 1643,
+  "플": 1644,
+  "픔": 1645,
+  "픕": 1646,
+  "피": 1647,
+  "픽": 1648,
+  "핀": 1649,
+  "필": 1650,
+  "핏": 1651,
+  "핑": 1652,
+  "하": 1653,
+  "학": 1654,
+  "한": 1655,
+  "할": 1656,
+  "핥": 1657,
+  "함": 1658,
+  "합": 1659,
+  "핫": 1660,
+  "항": 1661,
+  "핰": 1662,
+  "해": 1663,
+  "핵": 1664,
+  "핸": 1665,
+  "핼": 1666,
+  "햄": 1667,
+  "햅": 1668,
+  "햇": 1669,
+  "했": 1670,
+  "행": 1671,
+  "햠": 1672,
+  "향": 1673,
+  "허": 1674,
+  "헉": 1675,
+  "헌": 1676,
+  "헐": 1677,
+  "험": 1678,
+  "헛": 1679,
+  "헝": 1680,
+  "헤": 1681,
+  "헥": 1682,
+  "헨": 1683,
+  "헬": 1684,
+  "헴": 1685,
+  "헵": 1686,
+  "헷": 1687,
+  "헹": 1688,
+  "혀": 1689,
+  "혁": 1690,
+  "현": 1691,
+  "혈": 1692,
+  "혐": 1693,
+  "협": 1694,
+  "혓": 1695,
+  "혔": 1696,
+  "형": 1697,
+  "혜": 1698,
+  "호": 1699,
+  "혹": 1700,
+  "혼": 1701,
+  "홀": 1702,
+  "홈": 1703,
+  "홉": 1704,
+  "홋": 1705,
+  "홍": 1706,
+  "화": 1707,
+  "확": 1708,
+  "환": 1709,
+  "활": 1710,
+  "홥": 1711,
+  "황": 1712,
+  "회": 1713,
+  "획": 1714,
+  "횐": 1715,
+  "횟": 1716,
+  "횡": 1717,
+  "효": 1718,
+  "횩": 1719,
+  "후": 1720,
+  "훅": 1721,
+  "훈": 1722,
+  "훌": 1723,
+  "훑": 1724,
+  "훔": 1725,
+  "훕": 1726,
+  "훗": 1727,
+  "훠": 1728,
+  "훨": 1729,
+  "훼": 1730,
+  "휀": 1731,
+  "휑": 1732,
+  "휘": 1733,
+  "휙": 1734,
+  "휜": 1735,
+  "휠": 1736,
+  "휴": 1737,
+  "휸": 1738,
+  "흉": 1739,
+  "흐": 1740,
+  "흑": 1741,
+  "흔": 1742,
+  "흘": 1743,
+  "흙": 1744,
+  "흠": 1745,
+  "흡": 1746,
+  "흣": 1747,
+  "흥": 1748,
+  "흩": 1749,
+  "희": 1750,
+  "흰": 1751,
+  "히": 1752,
+  "힌": 1753,
+  "힐": 1754,
+  "힘": 1755,
+  "힙": 1756,
+  "힝": 1757
+}