commit 10130436997cb59f4d61f43f2ccbf1c04dccf941 Author: ModelHub XC Date: Tue May 19 02:28:43 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: syp1229/wav2vec2-large-xls-r-300m-korean_y_freq Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e81778 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +license: apache-2.0 +base_model: facebook/wav2vec2-xls-r-300m +tags: +- generated_from_trainer +model-index: +- name: wav2vec2-large-xls-r-300m-korean_y_freq + results: [] +--- + + + +# wav2vec2-large-xls-r-300m-korean_y_freq + +This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset. +It achieves the following results on the evaluation set: +- Loss: 0.4522 +- Cer: 13.5023 + +## 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: 0.0001 +- train_batch_size: 8 +- eval_batch_size: 8 +- seed: 42 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: linear +- lr_scheduler_warmup_steps: 100 +- num_epochs: 5 +- mixed_precision_training: Native AMP + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | Cer | +|:-------------:|:-----:|:----:|:---------------:|:-------:| +| 35.2803 | 0.13 | 200 | 5.5453 | 100.0 | +| 4.6452 | 0.26 | 400 | 4.6065 | 100.0 | +| 4.5568 | 0.39 | 600 | 4.5732 | 97.9643 | +| 4.492 | 0.52 | 800 | 4.5091 | 97.9643 | +| 4.343 | 0.64 | 1000 | 4.2369 | 95.5012 | +| 3.3778 | 0.77 | 1200 | 2.7151 | 49.3917 | +| 2.4127 | 0.9 | 1400 | 2.2297 | 42.1509 | +| 2.0113 | 1.03 | 1600 | 1.8500 | 35.5926 | +| 1.7037 | 1.16 | 1800 | 1.5783 | 31.7942 | +| 1.502 | 1.29 | 2000 | 1.4251 | 29.2184 | +| 1.3376 | 1.42 | 2200 | 1.3812 | 30.4232 | +| 1.2586 | 1.55 | 2400 | 1.1952 | 25.6751 | +| 1.1415 | 1.68 | 2600 | 1.1614 | 25.8176 | +| 1.0858 | 1.81 | 2800 | 1.0985 | 24.9154 | +| 0.9846 | 1.93 | 3000 | 0.9985 | 21.8826 | +| 0.9443 | 2.06 | 3200 | 0.8759 | 19.9359 | +| 0.8298 | 2.19 | 3400 | 0.8549 | 19.5798 | +| 0.8111 | 2.32 | 3600 | 0.8271 | 22.2506 | +| 0.7507 | 2.45 | 3800 | 0.7808 | 20.9389 | +| 0.7202 | 2.58 | 4000 | 0.7409 | 19.5323 | +| 0.7121 | 2.71 | 4200 | 0.7139 | 18.5649 | +| 0.6639 | 2.84 | 4400 | 0.6726 | 17.4669 | +| 0.6595 | 2.97 | 4600 | 0.6830 | 16.6301 | +| 0.6161 | 3.09 | 4800 | 0.6334 | 15.5677 | +| 0.5604 | 3.22 | 5000 | 0.5943 | 14.4460 | +| 0.5387 | 3.35 | 5200 | 0.6169 | 15.4727 | +| 0.5317 | 3.48 | 5400 | 0.5831 | 15.0751 | +| 0.5171 | 3.61 | 5600 | 0.5414 | 14.3807 | +| 0.5 | 3.74 | 5800 | 0.5307 | 14.1789 | +| 0.4888 | 3.87 | 6000 | 0.5171 | 14.4875 | +| 0.4826 | 4.0 | 6200 | 0.5011 | 13.9712 | +| 0.4311 | 4.13 | 6400 | 0.5131 | 14.2679 | +| 0.4178 | 4.26 | 6600 | 0.4929 | 14.0364 | +| 0.3999 | 4.38 | 6800 | 0.4791 | 14.3451 | +| 0.4029 | 4.51 | 7000 | 0.4885 | 13.8584 | +| 0.3922 | 4.64 | 7200 | 0.4759 | 14.2323 | +| 0.3804 | 4.77 | 7400 | 0.4584 | 13.6091 | +| 0.3748 | 4.9 | 7600 | 0.4522 | 13.5023 | + + +### Framework versions + +- Transformers 4.35.2 +- Pytorch 2.1.0+cu121 +- Datasets 2.16.0 +- Tokenizers 0.15.0 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..5a5a44c --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,4 @@ +{ + "": 1286, + "": 1285 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..edb2fe0 --- /dev/null +++ b/config.json @@ -0,0 +1,109 @@ +{ + "_name_or_path": "facebook/wav2vec2-xls-r-300m", + "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": 0.0, + "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": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.0, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.05, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "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": 1284, + "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": "4.35.2", + "use_weighted_layer_sum": false, + "vocab_size": 1287, + "xvector_output_dim": 512 +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..8669ec3 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cae0cc8d44799bc05c155ff3a091f8f2638676d044fc16d54f866966c964abe +size 1267084196 diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..73caa15 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,9 @@ +{ + "do_normalize": true, + "feature_extractor_type": "Wav2Vec2FeatureExtractor", + "feature_size": 1, + "padding_side": "right", + "padding_value": 0.0, + "return_attention_mask": true, + "sampling_rate": 16000 +} diff --git a/runs/Dec21_08-40-45_2f1d1adafa39/events.out.tfevents.1703148532.2f1d1adafa39.2100.0 b/runs/Dec21_08-40-45_2f1d1adafa39/events.out.tfevents.1703148532.2f1d1adafa39.2100.0 new file mode 100644 index 0000000..c3581b8 --- /dev/null +++ b/runs/Dec21_08-40-45_2f1d1adafa39/events.out.tfevents.1703148532.2f1d1adafa39.2100.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3618a913824c32afb051638a06cacf1bb507355d4a7b9717e1a4b192619547be +size 17009 diff --git a/runs/Dec21_10-57-39_ea79bdc770c0/events.out.tfevents.1703156743.ea79bdc770c0.1222.0 b/runs/Dec21_10-57-39_ea79bdc770c0/events.out.tfevents.1703156743.ea79bdc770c0.1222.0 new file mode 100644 index 0000000..a4ca3bb --- /dev/null +++ b/runs/Dec21_10-57-39_ea79bdc770c0/events.out.tfevents.1703156743.ea79bdc770c0.1222.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da8015775e564ea468a7ac6a5d6536c4005ea12d514e13c3380fd7055c4e67f +size 24135 diff --git a/runs/Dec21_15-06-08_182ed1786fd9/events.out.tfevents.1703171670.182ed1786fd9.908.0 b/runs/Dec21_15-06-08_182ed1786fd9/events.out.tfevents.1703171670.182ed1786fd9.908.0 new file mode 100644 index 0000000..513dfd4 --- /dev/null +++ b/runs/Dec21_15-06-08_182ed1786fd9/events.out.tfevents.1703171670.182ed1786fd9.908.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83549e0ff065c481b0570295a13c1f8905bd5559814ccf673509010f98eef304 +size 24134 diff --git a/runs/Dec22_02-14-43_1d9fe1eec548/events.out.tfevents.1703211808.1d9fe1eec548.554.0 b/runs/Dec22_02-14-43_1d9fe1eec548/events.out.tfevents.1703211808.1d9fe1eec548.554.0 new file mode 100644 index 0000000..50f6bff --- /dev/null +++ b/runs/Dec22_02-14-43_1d9fe1eec548/events.out.tfevents.1703211808.1d9fe1eec548.554.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1336d0507adebeedd0d4126e46136686e7c2b79d1018826e7d00684a6f704c9 +size 24135 diff --git a/runs/Dec22_08-11-10_a80a22ebecf0/events.out.tfevents.1703233168.a80a22ebecf0.567.0 b/runs/Dec22_08-11-10_a80a22ebecf0/events.out.tfevents.1703233168.a80a22ebecf0.567.0 new file mode 100644 index 0000000..c046e24 --- /dev/null +++ b/runs/Dec22_08-11-10_a80a22ebecf0/events.out.tfevents.1703233168.a80a22ebecf0.567.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72994f6a45d9b60f5e418b59ad2b3633cacc57afadc5a906ae9d13c484576727 +size 24134 diff --git a/runs/Dec22_13-39-42_5ca8f87b04e2/events.out.tfevents.1703252958.5ca8f87b04e2.1491.0 b/runs/Dec22_13-39-42_5ca8f87b04e2/events.out.tfevents.1703252958.5ca8f87b04e2.1491.0 new file mode 100644 index 0000000..0a26201 --- /dev/null +++ b/runs/Dec22_13-39-42_5ca8f87b04e2/events.out.tfevents.1703252958.5ca8f87b04e2.1491.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2f6c90014169ea8d3d26f20eb112608fbb6f39ac48ce48caa35551d2615b01 +size 26035 diff --git a/runs/Dec22_23-51-04_6c73bee96b67/events.out.tfevents.1703289758.6c73bee96b67.1451.0 b/runs/Dec22_23-51-04_6c73bee96b67/events.out.tfevents.1703289758.6c73bee96b67.1451.0 new file mode 100644 index 0000000..c48bd6a --- /dev/null +++ b/runs/Dec22_23-51-04_6c73bee96b67/events.out.tfevents.1703289758.6c73bee96b67.1451.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d323b83d2688c1189ff967caeb6650cd5cea2edfa724d9739b22d8bea5a3a3 +size 11431 diff --git a/runs/Dec23_01-43-02_6c73bee96b67/events.out.tfevents.1703296343.6c73bee96b67.1451.1 b/runs/Dec23_01-43-02_6c73bee96b67/events.out.tfevents.1703296343.6c73bee96b67.1451.1 new file mode 100644 index 0000000..3f75582 --- /dev/null +++ b/runs/Dec23_01-43-02_6c73bee96b67/events.out.tfevents.1703296343.6c73bee96b67.1451.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0f387f9c8aa49fa0629c517641a06631f98396a9a920ca288fc076a523f4ec +size 24135 diff --git a/runs/Dec23_07-39-58_6c73bee96b67/events.out.tfevents.1703317697.6c73bee96b67.118717.0 b/runs/Dec23_07-39-58_6c73bee96b67/events.out.tfevents.1703317697.6c73bee96b67.118717.0 new file mode 100644 index 0000000..43bafa8 --- /dev/null +++ b/runs/Dec23_07-39-58_6c73bee96b67/events.out.tfevents.1703317697.6c73bee96b67.118717.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00638984d2a495ff907232eca111d6b4b75a444730e1ecb279153132d5a1e7d5 +size 7631 diff --git a/runs/Dec23_08-39-56_18b033eeff48/events.out.tfevents.1703321328.18b033eeff48.2396.0 b/runs/Dec23_08-39-56_18b033eeff48/events.out.tfevents.1703321328.18b033eeff48.2396.0 new file mode 100644 index 0000000..a7cac8b --- /dev/null +++ b/runs/Dec23_08-39-56_18b033eeff48/events.out.tfevents.1703321328.18b033eeff48.2396.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde71ed7a49c04a5a353c22e07cd21b21663b72c7edc57ec0cff816d58251177 +size 24135 diff --git a/runs/Dec23_14-06-54_00234509e104/events.out.tfevents.1703341028.00234509e104.5239.0 b/runs/Dec23_14-06-54_00234509e104/events.out.tfevents.1703341028.00234509e104.5239.0 new file mode 100644 index 0000000..e9c9ab7 --- /dev/null +++ b/runs/Dec23_14-06-54_00234509e104/events.out.tfevents.1703341028.00234509e104.5239.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f799c7cccc12f47e5bfbdb394a6405e989628fa8477685aa060b1a4cdf373c1e +size 24135 diff --git a/runs/Dec24_00-42-46_0e345381eb5e/events.out.tfevents.1703379054.0e345381eb5e.581.0 b/runs/Dec24_00-42-46_0e345381eb5e/events.out.tfevents.1703379054.0e345381eb5e.581.0 new file mode 100644 index 0000000..57e665b --- /dev/null +++ b/runs/Dec24_00-42-46_0e345381eb5e/events.out.tfevents.1703379054.0e345381eb5e.581.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35a5916fed32d72c884d623b16b5ff5740b80c10aa17be38e90e5ed213b6c8a +size 24135 diff --git a/runs/Dec24_00-51-24_84bcd0d5a3bd/events.out.tfevents.1703379572.84bcd0d5a3bd.3269.0 b/runs/Dec24_00-51-24_84bcd0d5a3bd/events.out.tfevents.1703379572.84bcd0d5a3bd.3269.0 new file mode 100644 index 0000000..ee65e15 --- /dev/null +++ b/runs/Dec24_00-51-24_84bcd0d5a3bd/events.out.tfevents.1703379572.84bcd0d5a3bd.3269.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37851e5b7450ffac4cd355869efe7c6f4bcf8eb1302a8d301b56eb243c59672c +size 24135 diff --git a/runs/Dec24_01-02-01_2d39320b9ba4/events.out.tfevents.1703380238.2d39320b9ba4.828.0 b/runs/Dec24_01-02-01_2d39320b9ba4/events.out.tfevents.1703380238.2d39320b9ba4.828.0 new file mode 100644 index 0000000..bae0a11 --- /dev/null +++ b/runs/Dec24_01-02-01_2d39320b9ba4/events.out.tfevents.1703380238.2d39320b9ba4.828.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e2e16eb3b527f396cdda8e60308891f8a96270233e55ef01079e557d37e5d42 +size 24135 diff --git a/runs/Dec24_08-19-41_155151bae98a/events.out.tfevents.1703406488.155151bae98a.3755.0 b/runs/Dec24_08-19-41_155151bae98a/events.out.tfevents.1703406488.155151bae98a.3755.0 new file mode 100644 index 0000000..c266189 --- /dev/null +++ b/runs/Dec24_08-19-41_155151bae98a/events.out.tfevents.1703406488.155151bae98a.3755.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff35febb2d13c551f46fb3a7766572db3a75c1e6aa4a269a46ce4cc7bcc68e38 +size 24135 diff --git a/runs/Dec24_08-25-41_f6b61e75ffff/events.out.tfevents.1703406871.f6b61e75ffff.3191.0 b/runs/Dec24_08-25-41_f6b61e75ffff/events.out.tfevents.1703406871.f6b61e75ffff.3191.0 new file mode 100644 index 0000000..3817741 --- /dev/null +++ b/runs/Dec24_08-25-41_f6b61e75ffff/events.out.tfevents.1703406871.f6b61e75ffff.3191.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa43682eb188524cb38ad49d67497a7b4ef0baff0d7f0d8bc683a26915e2dd4 +size 24135 diff --git a/runs/Dec24_08-37-11_aa68334b530f/events.out.tfevents.1703407642.aa68334b530f.925.0 b/runs/Dec24_08-37-11_aa68334b530f/events.out.tfevents.1703407642.aa68334b530f.925.0 new file mode 100644 index 0000000..179d77a --- /dev/null +++ b/runs/Dec24_08-37-11_aa68334b530f/events.out.tfevents.1703407642.aa68334b530f.925.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17fbb7759e99a518ca406b04ae14382c5934fd31a75c932d7b4639c3d3a191be +size 24135 diff --git a/runs/Dec24_13-57-28_69270c537cc3/events.out.tfevents.1703426935.69270c537cc3.438.0 b/runs/Dec24_13-57-28_69270c537cc3/events.out.tfevents.1703426935.69270c537cc3.438.0 new file mode 100644 index 0000000..a9a28f0 --- /dev/null +++ b/runs/Dec24_13-57-28_69270c537cc3/events.out.tfevents.1703426935.69270c537cc3.438.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13608a6883a29d47579ccb3997a440fcb43345cf2c1a9585893b2e0ead3a082d +size 24136 diff --git a/runs/Dec24_14-00-30_7fbfebaa35eb/events.out.tfevents.1703427000.7fbfebaa35eb.607.0 b/runs/Dec24_14-00-30_7fbfebaa35eb/events.out.tfevents.1703427000.7fbfebaa35eb.607.0 new file mode 100644 index 0000000..07816d5 --- /dev/null +++ b/runs/Dec24_14-00-30_7fbfebaa35eb/events.out.tfevents.1703427000.7fbfebaa35eb.607.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679318724ef18245a7b96f227d7a4cbb824b66d395c8960b9f07a3c4b24f8fc5 +size 24136 diff --git a/runs/Dec24_14-02-13_24d530e98ee9/events.out.tfevents.1703427089.24d530e98ee9.516.0 b/runs/Dec24_14-02-13_24d530e98ee9/events.out.tfevents.1703427089.24d530e98ee9.516.0 new file mode 100644 index 0000000..8c7fd6c --- /dev/null +++ b/runs/Dec24_14-02-13_24d530e98ee9/events.out.tfevents.1703427089.24d530e98ee9.516.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58b7e97116591c756d6c7b52ca33a5d13e4d0b951c8eb882143335d850a3279 +size 24136 diff --git a/runs/Dec25_01-22-54_148d4d730a15/events.out.tfevents.1703467850.148d4d730a15.6045.0 b/runs/Dec25_01-22-54_148d4d730a15/events.out.tfevents.1703467850.148d4d730a15.6045.0 new file mode 100644 index 0000000..cae6258 --- /dev/null +++ b/runs/Dec25_01-22-54_148d4d730a15/events.out.tfevents.1703467850.148d4d730a15.6045.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1d89dcbd7af88c3d7ef3c7029892b93788d7e9fdf38109bf4ae7ed251fd075 +size 24136 diff --git a/runs/Dec25_01-29-52_71e099da6fcc/events.out.tfevents.1703468366.71e099da6fcc.437.0 b/runs/Dec25_01-29-52_71e099da6fcc/events.out.tfevents.1703468366.71e099da6fcc.437.0 new file mode 100644 index 0000000..0f56c11 --- /dev/null +++ b/runs/Dec25_01-29-52_71e099da6fcc/events.out.tfevents.1703468366.71e099da6fcc.437.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ec74182046b7cf6f36d973ce834418670f1775d048e8eb3691cfd7fa5a275d +size 24136 diff --git a/runs/Dec25_01-34-02_64d1b392cad9/events.out.tfevents.1703468596.64d1b392cad9.6026.0 b/runs/Dec25_01-34-02_64d1b392cad9/events.out.tfevents.1703468596.64d1b392cad9.6026.0 new file mode 100644 index 0000000..f5312c9 --- /dev/null +++ b/runs/Dec25_01-34-02_64d1b392cad9/events.out.tfevents.1703468596.64d1b392cad9.6026.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739a06e0200da9b10b4f973a7d12bce3209f972c295b50581daf0b53e8ef6796 +size 24136 diff --git a/runs/Dec25_08-00-47_a389e3a390ed/events.out.tfevents.1703491781.a389e3a390ed.2804.0 b/runs/Dec25_08-00-47_a389e3a390ed/events.out.tfevents.1703491781.a389e3a390ed.2804.0 new file mode 100644 index 0000000..7a756f8 --- /dev/null +++ b/runs/Dec25_08-00-47_a389e3a390ed/events.out.tfevents.1703491781.a389e3a390ed.2804.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54dc94c5c24fc6529a86e29de1a1b47ffe73a719d1930ac517d74c84ee47f7ad +size 24136 diff --git a/runs/Dec25_08-14-36_ce10200ecc23/events.out.tfevents.1703492569.ce10200ecc23.3347.0 b/runs/Dec25_08-14-36_ce10200ecc23/events.out.tfevents.1703492569.ce10200ecc23.3347.0 new file mode 100644 index 0000000..d00c208 --- /dev/null +++ b/runs/Dec25_08-14-36_ce10200ecc23/events.out.tfevents.1703492569.ce10200ecc23.3347.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d97d11736bfebeed7af61bd028ea92bc005dfd03132469aa064557662c07cdb +size 24136 diff --git a/runs/Dec25_08-25-18_959a978cf40c/events.out.tfevents.1703493304.959a978cf40c.1243.0 b/runs/Dec25_08-25-18_959a978cf40c/events.out.tfevents.1703493304.959a978cf40c.1243.0 new file mode 100644 index 0000000..0e1d2e6 --- /dev/null +++ b/runs/Dec25_08-25-18_959a978cf40c/events.out.tfevents.1703493304.959a978cf40c.1243.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f61d4fe1cc8323b2e3117ccff7cfb4f29b08edd9ff1db464a4a75d2dabb2c9d +size 24136 diff --git a/runs/Dec25_14-58-12_811c31ac50a1/events.out.tfevents.1703516783.811c31ac50a1.1195.0 b/runs/Dec25_14-58-12_811c31ac50a1/events.out.tfevents.1703516783.811c31ac50a1.1195.0 new file mode 100644 index 0000000..d3b5588 --- /dev/null +++ b/runs/Dec25_14-58-12_811c31ac50a1/events.out.tfevents.1703516783.811c31ac50a1.1195.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9895492e06504fcbfb8c8e25050e99b2961cbd84a70a080bb3824373372f8a +size 24136 diff --git a/runs/Dec25_14-58-12_830e9540a655/events.out.tfevents.1703516772.830e9540a655.1714.0 b/runs/Dec25_14-58-12_830e9540a655/events.out.tfevents.1703516772.830e9540a655.1714.0 new file mode 100644 index 0000000..40b5f02 --- /dev/null +++ b/runs/Dec25_14-58-12_830e9540a655/events.out.tfevents.1703516772.830e9540a655.1714.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18b2b840c8beda01c425abaf75b806bfc2f536ab03892f0da3fd4bf1303d66a +size 24136 diff --git a/runs/Dec25_15-00-19_868b54fb3ad5/events.out.tfevents.1703516936.868b54fb3ad5.1209.0 b/runs/Dec25_15-00-19_868b54fb3ad5/events.out.tfevents.1703516936.868b54fb3ad5.1209.0 new file mode 100644 index 0000000..b61af22 --- /dev/null +++ b/runs/Dec25_15-00-19_868b54fb3ad5/events.out.tfevents.1703516936.868b54fb3ad5.1209.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd3ccecbba53cd0158fd172ef1492f01dee8b3f1911bfc7b667457023d13265 +size 24136 diff --git a/runs/Dec26_04-41-21_6e2d352d5a53/events.out.tfevents.1703566308.6e2d352d5a53.2383.0 b/runs/Dec26_04-41-21_6e2d352d5a53/events.out.tfevents.1703566308.6e2d352d5a53.2383.0 new file mode 100644 index 0000000..2bb3ded --- /dev/null +++ b/runs/Dec26_04-41-21_6e2d352d5a53/events.out.tfevents.1703566308.6e2d352d5a53.2383.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a350903106ea36c2e043238338d8079fbf682b3757852be4fe1c3593362ef96 +size 24136 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1c2a036 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "[PAD]", + "unk_token": "[UNK]" +} diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..469e67f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,47 @@ +{ + "added_tokens_decoder": { + "1283": { + "content": "[UNK]", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "1284": { + "content": "[PAD]", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "1285": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1286": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": true, + "do_lower_case": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "[PAD]", + "replace_word_delimiter_char": " ", + "target_lang": null, + "tokenizer_class": "Wav2Vec2CTCTokenizer", + "unk_token": "[UNK]", + "word_delimiter_token": "|" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..95d526d --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387a0451718c2c0e06feb6544f8533e06c26033966f56fd5dfd792a3f485e83c +size 4600 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..143949d --- /dev/null +++ b/vocab.json @@ -0,0 +1,1287 @@ +{ + "(": 1, + ")": 2, + "[PAD]": 1284, + "[UNK]": 1283, + "\\": 3, + "a": 4, + "f": 5, + "n": 6, + "o": 7, + "p": 8, + "s": 9, + "|": 0, + "가": 10, + "각": 11, + "간": 12, + "갇": 13, + "갈": 14, + "갉": 15, + "감": 16, + "갑": 17, + "값": 18, + "갓": 19, + "갔": 20, + "강": 21, + "갖": 22, + "같": 23, + "갚": 24, + "갛": 25, + "개": 26, + "객": 27, + "갠": 28, + "갱": 29, + "걀": 30, + "걔": 31, + "거": 32, + "걱": 33, + "건": 34, + "걷": 35, + "걸": 36, + "검": 37, + "겁": 38, + "것": 39, + "겄": 40, + "겉": 41, + "게": 42, + "겐": 43, + "겟": 44, + "겠": 45, + "겨": 46, + "격": 47, + "겪": 48, + "견": 49, + "결": 50, + "겸": 51, + "겹": 52, + "겼": 53, + "경": 54, + "곁": 55, + "계": 56, + "고": 57, + "곡": 58, + "곤": 59, + "곧": 60, + "골": 61, + "곰": 62, + "곱": 63, + "곳": 64, + "공": 65, + "곶": 66, + "과": 67, + "곽": 68, + "관": 69, + "괄": 70, + "괌": 71, + "광": 72, + "괜": 73, + "괴": 74, + "굉": 75, + "교": 76, + "굑": 77, + "구": 78, + "국": 79, + "군": 80, + "굳": 81, + "굴": 82, + "굵": 83, + "굶": 84, + "굽": 85, + "궁": 86, + "궂": 87, + "궈": 88, + "권": 89, + "궐": 90, + "귀": 91, + "규": 92, + "균": 93, + "귤": 94, + "그": 95, + "극": 96, + "근": 97, + "글": 98, + "긁": 99, + "금": 100, + "급": 101, + "긋": 102, + "긍": 103, + "기": 104, + "긱": 105, + "긴": 106, + "길": 107, + "김": 108, + "깁": 109, + "깃": 110, + "깅": 111, + "깊": 112, + "까": 113, + "깍": 114, + "깎": 115, + "깐": 116, + "깔": 117, + "깜": 118, + "깝": 119, + "깠": 120, + "깡": 121, + "깥": 122, + "깨": 123, + "깻": 124, + "깼": 125, + "꺼": 126, + "꺽": 127, + "꺾": 128, + "껀": 129, + "껍": 130, + "껏": 131, + "껑": 132, + "께": 133, + "껫": 134, + "껴": 135, + "꼈": 136, + "꼬": 137, + "꼭": 138, + "꼴": 139, + "꼼": 140, + "꼽": 141, + "꽁": 142, + "꽂": 143, + "꽃": 144, + "꽈": 145, + "꽉": 146, + "꽙": 147, + "꽝": 148, + "꽤": 149, + "꾸": 150, + "꾹": 151, + "꾼": 152, + "꿀": 153, + "꿇": 154, + "꿈": 155, + "꿍": 156, + "꿔": 157, + "꿨": 158, + "꿰": 159, + "뀌": 160, + "뀐": 161, + "뀔": 162, + "끄": 163, + "끈": 164, + "끊": 165, + "끌": 166, + "끍": 167, + "끓": 168, + "끔": 169, + "끗": 170, + "끝": 171, + "끼": 172, + "끽": 173, + "낀": 174, + "낄": 175, + "낌": 176, + "나": 177, + "낙": 178, + "낚": 179, + "난": 180, + "날": 181, + "낡": 182, + "남": 183, + "납": 184, + "낫": 185, + "났": 186, + "낭": 187, + "낮": 188, + "낱": 189, + "낳": 190, + "내": 191, + "낸": 192, + "낼": 193, + "냄": 194, + "냅": 195, + "냈": 196, + "냉": 197, + "냐": 198, + "냥": 199, + "너": 200, + "넉": 201, + "넌": 202, + "널": 203, + "넓": 204, + "넘": 205, + "넙": 206, + "넣": 207, + "네": 208, + "넷": 209, + "녀": 210, + "녁": 211, + "년": 212, + "념": 213, + "녔": 214, + "녕": 215, + "노": 216, + "녹": 217, + "논": 218, + "놀": 219, + "놈": 220, + "농": 221, + "높": 222, + "놓": 223, + "놔": 224, + "놨": 225, + "뇌": 226, + "뇨": 227, + "누": 228, + "눈": 229, + "눌": 230, + "눕": 231, + "눠": 232, + "눴": 233, + "뉴": 234, + "느": 235, + "늑": 236, + "는": 237, + "늘": 238, + "늙": 239, + "늠": 240, + "능": 241, + "늦": 242, + "늬": 243, + "니": 244, + "닉": 245, + "닌": 246, + "닐": 247, + "님": 248, + "닙": 249, + "닝": 250, + "다": 251, + "닥": 252, + "닦": 253, + "단": 254, + "닫": 255, + "달": 256, + "닭": 257, + "닮": 258, + "담": 259, + "답": 260, + "닷": 261, + "당": 262, + "닿": 263, + "대": 264, + "댁": 265, + "댄": 266, + "댈": 267, + "댐": 268, + "댑": 269, + "댓": 270, + "댔": 271, + "댕": 272, + "더": 273, + "덕": 274, + "던": 275, + "덜": 276, + "덟": 277, + "덤": 278, + "덥": 279, + "덧": 280, + "덩": 281, + "덮": 282, + "데": 283, + "덴": 284, + "델": 285, + "뎌": 286, + "도": 287, + "독": 288, + "돈": 289, + "돋": 290, + "돌": 291, + "돔": 292, + "돕": 293, + "동": 294, + "돼": 295, + "됐": 296, + "되": 297, + "된": 298, + "될": 299, + "됨": 300, + "됩": 301, + "두": 302, + "둑": 303, + "둔": 304, + "둘": 305, + "둡": 306, + "둥": 307, + "둬": 308, + "뒀": 309, + "뒤": 310, + "뒷": 311, + "뒹": 312, + "드": 313, + "득": 314, + "든": 315, + "듣": 316, + "들": 317, + "듬": 318, + "듭": 319, + "듯": 320, + "등": 321, + "디": 322, + "딘": 323, + "딜": 324, + "딨": 325, + "딩": 326, + "딪": 327, + "따": 328, + "딱": 329, + "딴": 330, + "딸": 331, + "땀": 332, + "땄": 333, + "땅": 334, + "때": 335, + "땍": 336, + "땐": 337, + "땜": 338, + "땠": 339, + "땡": 340, + "떄": 341, + "떠": 342, + "떡": 343, + "떤": 344, + "떨": 345, + "떳": 346, + "떴": 347, + "떻": 348, + "떼": 349, + "또": 350, + "똑": 351, + "똘": 352, + "똥": 353, + "뚜": 354, + "뚝": 355, + "뚫": 356, + "뚱": 357, + "뛰": 358, + "뛴": 359, + "뜨": 360, + "뜩": 361, + "뜬": 362, + "뜯": 363, + "뜰": 364, + "뜹": 365, + "뜻": 366, + "띃": 367, + "띄": 368, + "띠": 369, + "띵": 370, + "라": 371, + "락": 372, + "란": 373, + "랄": 374, + "람": 375, + "랍": 376, + "랏": 377, + "랐": 378, + "랑": 379, + "랗": 380, + "래": 381, + "랜": 382, + "램": 383, + "랫": 384, + "랬": 385, + "랭": 386, + "랴": 387, + "략": 388, + "량": 389, + "러": 390, + "럭": 391, + "런": 392, + "럴": 393, + "럼": 394, + "럽": 395, + "럿": 396, + "렀": 397, + "렁": 398, + "렇": 399, + "레": 400, + "렉": 401, + "렌": 402, + "렛": 403, + "려": 404, + "력": 405, + "련": 406, + "렬": 407, + "렴": 408, + "렵": 409, + "렸": 410, + "령": 411, + "례": 412, + "로": 413, + "록": 414, + "론": 415, + "롤": 416, + "롭": 417, + "롯": 418, + "롱": 419, + "뢰": 420, + "료": 421, + "룡": 422, + "루": 423, + "룩": 424, + "룬": 425, + "룰": 426, + "룸": 427, + "룻": 428, + "뤄": 429, + "뤘": 430, + "류": 431, + "륙": 432, + "륜": 433, + "률": 434, + "륨": 435, + "륭": 436, + "르": 437, + "륵": 438, + "른": 439, + "를": 440, + "름": 441, + "릇": 442, + "릉": 443, + "릎": 444, + "릏": 445, + "리": 446, + "릭": 447, + "린": 448, + "릴": 449, + "림": 450, + "립": 451, + "릿": 452, + "링": 453, + "마": 454, + "막": 455, + "만": 456, + "많": 457, + "맏": 458, + "말": 459, + "맑": 460, + "맘": 461, + "맙": 462, + "맛": 463, + "망": 464, + "맞": 465, + "맡": 466, + "맣": 467, + "매": 468, + "맥": 469, + "맨": 470, + "맵": 471, + "맸": 472, + "맹": 473, + "맺": 474, + "머": 475, + "먹": 476, + "먼": 477, + "멀": 478, + "멈": 479, + "멋": 480, + "멍": 481, + "메": 482, + "멘": 483, + "멜": 484, + "멤": 485, + "멧": 486, + "며": 487, + "면": 488, + "멸": 489, + "명": 490, + "몇": 491, + "모": 492, + "목": 493, + "몫": 494, + "몬": 495, + "몰": 496, + "몸": 497, + "못": 498, + "몽": 499, + "묘": 500, + "무": 501, + "묵": 502, + "묶": 503, + "문": 504, + "묻": 505, + "물": 506, + "뭇": 507, + "뭉": 508, + "뭐": 509, + "뭔": 510, + "뭘": 511, + "뭡": 512, + "뭣": 513, + "뮤": 514, + "므": 515, + "믄": 516, + "미": 517, + "믹": 518, + "민": 519, + "믿": 520, + "밀": 521, + "밉": 522, + "밌": 523, + "밍": 524, + "밑": 525, + "바": 526, + "박": 527, + "밖": 528, + "반": 529, + "받": 530, + "발": 531, + "밝": 532, + "밟": 533, + "밤": 534, + "밥": 535, + "방": 536, + "밭": 537, + "배": 538, + "백": 539, + "뱃": 540, + "뱅": 541, + "뱉": 542, + "버": 543, + "벅": 544, + "번": 545, + "벌": 546, + "범": 547, + "법": 548, + "벗": 549, + "벚": 550, + "베": 551, + "벤": 552, + "벨": 553, + "벼": 554, + "벽": 555, + "변": 556, + "별": 557, + "볍": 558, + "볏": 559, + "병": 560, + "보": 561, + "복": 562, + "볶": 563, + "본": 564, + "볼": 565, + "봄": 566, + "봅": 567, + "봇": 568, + "봉": 569, + "봐": 570, + "봤": 571, + "봬": 572, + "뵙": 573, + "뵤": 574, + "부": 575, + "북": 576, + "분": 577, + "불": 578, + "붉": 579, + "붐": 580, + "붓": 581, + "붕": 582, + "붙": 583, + "뷔": 584, + "브": 585, + "블": 586, + "비": 587, + "빅": 588, + "빈": 589, + "빌": 590, + "빔": 591, + "빕": 592, + "빙": 593, + "빚": 594, + "빛": 595, + "빠": 596, + "빡": 597, + "빨": 598, + "빴": 599, + "빵": 600, + "빻": 601, + "빼": 602, + "빽": 603, + "뺀": 604, + "뺄": 605, + "뺏": 606, + "뺐": 607, + "뻐": 608, + "뻔": 609, + "뻘": 610, + "뻠": 611, + "뻣": 612, + "뻤": 613, + "뼈": 614, + "뽀": 615, + "뽈": 616, + "뽑": 617, + "뽕": 618, + "뿅": 619, + "뿌": 620, + "뿍": 621, + "뿐": 622, + "쁘": 623, + "쁜": 624, + "쁠": 625, + "쁨": 626, + "삐": 627, + "사": 628, + "삭": 629, + "산": 630, + "살": 631, + "삶": 632, + "삼": 633, + "삽": 634, + "삿": 635, + "샀": 636, + "상": 637, + "새": 638, + "색": 639, + "샌": 640, + "샐": 641, + "샘": 642, + "샛": 643, + "생": 644, + "샤": 645, + "샵": 646, + "샷": 647, + "서": 648, + "석": 649, + "섞": 650, + "선": 651, + "섣": 652, + "설": 653, + "섬": 654, + "섭": 655, + "섯": 656, + "섰": 657, + "성": 658, + "세": 659, + "센": 660, + "셀": 661, + "셋": 662, + "셔": 663, + "션": 664, + "셜": 665, + "셨": 666, + "셰": 667, + "소": 668, + "속": 669, + "손": 670, + "솔": 671, + "솜": 672, + "솟": 673, + "송": 674, + "솥": 675, + "쇄": 676, + "쇠": 677, + "쇳": 678, + "쇼": 679, + "숍": 680, + "수": 681, + "숙": 682, + "순": 683, + "숟": 684, + "술": 685, + "숨": 686, + "숫": 687, + "숭": 688, + "숯": 689, + "숲": 690, + "숴": 691, + "쉐": 692, + "쉘": 693, + "쉬": 694, + "쉰": 695, + "쉴": 696, + "쉼": 697, + "쉽": 698, + "슈": 699, + "슐": 700, + "슘": 701, + "스": 702, + "슨": 703, + "슬": 704, + "슭": 705, + "슴": 706, + "습": 707, + "슷": 708, + "승": 709, + "시": 710, + "식": 711, + "신": 712, + "싣": 713, + "실": 714, + "싫": 715, + "심": 716, + "십": 717, + "싱": 718, + "싶": 719, + "싷": 720, + "싸": 721, + "싹": 722, + "싼": 723, + "쌀": 724, + "쌈": 725, + "쌌": 726, + "쌍": 727, + "쌓": 728, + "쌤": 729, + "쌰": 730, + "써": 731, + "썩": 732, + "썬": 733, + "썰": 734, + "썼": 735, + "쎄": 736, + "쎗": 737, + "쏘": 738, + "쏙": 739, + "쏟": 740, + "쏠": 741, + "쐬": 742, + "쑈": 743, + "쑤": 744, + "쑥": 745, + "쓰": 746, + "쓴": 747, + "쓸": 748, + "씀": 749, + "씁": 750, + "씌": 751, + "씨": 752, + "씩": 753, + "씬": 754, + "씹": 755, + "씻": 756, + "씽": 757, + "아": 758, + "악": 759, + "안": 760, + "앉": 761, + "않": 762, + "알": 763, + "앓": 764, + "암": 765, + "압": 766, + "앗": 767, + "았": 768, + "앙": 769, + "앞": 770, + "애": 771, + "액": 772, + "앤": 773, + "앨": 774, + "앵": 775, + "야": 776, + "약": 777, + "얀": 778, + "얄": 779, + "얇": 780, + "얌": 781, + "양": 782, + "얗": 783, + "얘": 784, + "어": 785, + "억": 786, + "언": 787, + "얹": 788, + "얻": 789, + "얼": 790, + "얽": 791, + "엄": 792, + "업": 793, + "없": 794, + "엇": 795, + "었": 796, + "엉": 797, + "엊": 798, + "엎": 799, + "에": 800, + "엑": 801, + "엔": 802, + "엘": 803, + "엠": 804, + "여": 805, + "역": 806, + "엮": 807, + "연": 808, + "열": 809, + "염": 810, + "엽": 811, + "엿": 812, + "였": 813, + "영": 814, + "옆": 815, + "예": 816, + "옛": 817, + "오": 818, + "옥": 819, + "온": 820, + "올": 821, + "옮": 822, + "옳": 823, + "옵": 824, + "옷": 825, + "옹": 826, + "옻": 827, + "와": 828, + "완": 829, + "왈": 830, + "왓": 831, + "왔": 832, + "왕": 833, + "왜": 834, + "왠": 835, + "외": 836, + "왼": 837, + "요": 838, + "욕": 839, + "욜": 840, + "용": 841, + "우": 842, + "욱": 843, + "운": 844, + "울": 845, + "움": 846, + "웃": 847, + "웅": 848, + "워": 849, + "원": 850, + "월": 851, + "웠": 852, + "웨": 853, + "웬": 854, + "위": 855, + "윌": 856, + "윗": 857, + "윙": 858, + "유": 859, + "육": 860, + "윤": 861, + "율": 862, + "윳": 863, + "융": 864, + "으": 865, + "은": 866, + "을": 867, + "음": 868, + "읍": 869, + "응": 870, + "의": 871, + "이": 872, + "익": 873, + "인": 874, + "일": 875, + "읽": 876, + "잃": 877, + "임": 878, + "입": 879, + "잇": 880, + "있": 881, + "잉": 882, + "잊": 883, + "잎": 884, + "자": 885, + "작": 886, + "잔": 887, + "잖": 888, + "잘": 889, + "잠": 890, + "잡": 891, + "잣": 892, + "잤": 893, + "장": 894, + "잦": 895, + "재": 896, + "잰": 897, + "잴": 898, + "쟀": 899, + "쟁": 900, + "쟤": 901, + "저": 902, + "적": 903, + "전": 904, + "절": 905, + "젊": 906, + "점": 907, + "접": 908, + "젓": 909, + "정": 910, + "젖": 911, + "제": 912, + "젠": 913, + "젤": 914, + "져": 915, + "졌": 916, + "조": 917, + "족": 918, + "존": 919, + "졸": 920, + "좀": 921, + "좁": 922, + "종": 923, + "좋": 924, + "좌": 925, + "죄": 926, + "죠": 927, + "주": 928, + "죽": 929, + "준": 930, + "줄": 931, + "줌": 932, + "줍": 933, + "중": 934, + "줘": 935, + "줬": 936, + "쥐": 937, + "즈": 938, + "즉": 939, + "즌": 940, + "즐": 941, + "즘": 942, + "즙": 943, + "증": 944, + "지": 945, + "직": 946, + "진": 947, + "질": 948, + "짊": 949, + "짐": 950, + "집": 951, + "짓": 952, + "징": 953, + "짙": 954, + "짚": 955, + "짜": 956, + "짝": 957, + "짠": 958, + "짤": 959, + "짧": 960, + "짬": 961, + "짰": 962, + "짱": 963, + "째": 964, + "쨈": 965, + "쨋": 966, + "쨌": 967, + "쩌": 968, + "쩍": 969, + "쩐": 970, + "쩔": 971, + "쩜": 972, + "쩡": 973, + "쪄": 974, + "쪘": 975, + "쪼": 976, + "쪽": 977, + "쫀": 978, + "쫄": 979, + "쫌": 980, + "쫓": 981, + "쫙": 982, + "쬐": 983, + "쭈": 984, + "쭉": 985, + "쭤": 986, + "쯤": 987, + "찌": 988, + "찍": 989, + "찐": 990, + "찔": 991, + "찜": 992, + "찝": 993, + "찡": 994, + "찢": 995, + "차": 996, + "착": 997, + "찬": 998, + "찮": 999, + "찰": 1000, + "참": 1001, + "찹": 1002, + "찻": 1003, + "찼": 1004, + "창": 1005, + "찾": 1006, + "채": 1007, + "책": 1008, + "챙": 1009, + "처": 1010, + "척": 1011, + "천": 1012, + "철": 1013, + "첨": 1014, + "첩": 1015, + "첫": 1016, + "청": 1017, + "체": 1018, + "쳐": 1019, + "쳤": 1020, + "초": 1021, + "촉": 1022, + "촌": 1023, + "총": 1024, + "촬": 1025, + "최": 1026, + "쵸": 1027, + "추": 1028, + "축": 1029, + "춘": 1030, + "출": 1031, + "춤": 1032, + "춥": 1033, + "춧": 1034, + "충": 1035, + "춰": 1036, + "췄": 1037, + "췌": 1038, + "취": 1039, + "츠": 1040, + "측": 1041, + "츰": 1042, + "층": 1043, + "치": 1044, + "칙": 1045, + "친": 1046, + "칠": 1047, + "칡": 1048, + "침": 1049, + "칫": 1050, + "칭": 1051, + "카": 1052, + "칵": 1053, + "칸": 1054, + "칼": 1055, + "캄": 1056, + "캅": 1057, + "캉": 1058, + "캐": 1059, + "캠": 1060, + "캡": 1061, + "캤": 1062, + "커": 1063, + "컨": 1064, + "컬": 1065, + "컴": 1066, + "컵": 1067, + "컷": 1068, + "컸": 1069, + "케": 1070, + "켓": 1071, + "켜": 1072, + "켰": 1073, + "코": 1074, + "콕": 1075, + "콘": 1076, + "콜": 1077, + "콤": 1078, + "콧": 1079, + "콩": 1080, + "쾌": 1081, + "쿠": 1082, + "쿨": 1083, + "쿼": 1084, + "퀴": 1085, + "퀼": 1086, + "큐": 1087, + "크": 1088, + "큰": 1089, + "클": 1090, + "큼": 1091, + "키": 1092, + "킨": 1093, + "킬": 1094, + "킴": 1095, + "킹": 1096, + "타": 1097, + "탁": 1098, + "탄": 1099, + "탈": 1100, + "탐": 1101, + "탑": 1102, + "탔": 1103, + "탕": 1104, + "태": 1105, + "택": 1106, + "탤": 1107, + "탬": 1108, + "탱": 1109, + "터": 1110, + "턱": 1111, + "턴": 1112, + "털": 1113, + "텁": 1114, + "텃": 1115, + "텅": 1116, + "테": 1117, + "텍": 1118, + "텐": 1119, + "텔": 1120, + "템": 1121, + "토": 1122, + "톡": 1123, + "톤": 1124, + "톱": 1125, + "통": 1126, + "퇴": 1127, + "투": 1128, + "툭": 1129, + "툴": 1130, + "툼": 1131, + "퉁": 1132, + "튀": 1133, + "튈": 1134, + "튜": 1135, + "튤": 1136, + "트": 1137, + "특": 1138, + "튼": 1139, + "튿": 1140, + "틀": 1141, + "틈": 1142, + "티": 1143, + "틱": 1144, + "틴": 1145, + "틸": 1146, + "팀": 1147, + "팁": 1148, + "팅": 1149, + "파": 1150, + "팍": 1151, + "판": 1152, + "팔": 1153, + "팝": 1154, + "팠": 1155, + "팡": 1156, + "팥": 1157, + "패": 1158, + "팩": 1159, + "팬": 1160, + "팰": 1161, + "팻": 1162, + "팽": 1163, + "퍼": 1164, + "퍽": 1165, + "펄": 1166, + "펌": 1167, + "펑": 1168, + "페": 1169, + "펙": 1170, + "펜": 1171, + "펴": 1172, + "편": 1173, + "펼": 1174, + "폈": 1175, + "평": 1176, + "폐": 1177, + "포": 1178, + "폭": 1179, + "폰": 1180, + "폴": 1181, + "폼": 1182, + "표": 1183, + "푸": 1184, + "푹": 1185, + "푼": 1186, + "풀": 1187, + "품": 1188, + "풍": 1189, + "퓨": 1190, + "프": 1191, + "픈": 1192, + "플": 1193, + "픔": 1194, + "픕": 1195, + "피": 1196, + "픽": 1197, + "핀": 1198, + "필": 1199, + "핍": 1200, + "핏": 1201, + "핑": 1202, + "하": 1203, + "학": 1204, + "한": 1205, + "할": 1206, + "함": 1207, + "합": 1208, + "핫": 1209, + "핬": 1210, + "항": 1211, + "해": 1212, + "핵": 1213, + "핸": 1214, + "햄": 1215, + "햇": 1216, + "했": 1217, + "행": 1218, + "향": 1219, + "허": 1220, + "헌": 1221, + "헐": 1222, + "험": 1223, + "헛": 1224, + "헤": 1225, + "헥": 1226, + "헬": 1227, + "헷": 1228, + "혀": 1229, + "현": 1230, + "혈": 1231, + "혐": 1232, + "협": 1233, + "혔": 1234, + "형": 1235, + "혜": 1236, + "호": 1237, + "혹": 1238, + "혼": 1239, + "홀": 1240, + "홈": 1241, + "홉": 1242, + "홍": 1243, + "화": 1244, + "확": 1245, + "환": 1246, + "활": 1247, + "황": 1248, + "회": 1249, + "획": 1250, + "횟": 1251, + "횡": 1252, + "효": 1253, + "후": 1254, + "훅": 1255, + "훈": 1256, + "훌": 1257, + "훔": 1258, + "훗": 1259, + "훡": 1260, + "훨": 1261, + "훼": 1262, + "휘": 1263, + "휙": 1264, + "휠": 1265, + "휴": 1266, + "흉": 1267, + "흐": 1268, + "흑": 1269, + "흔": 1270, + "흘": 1271, + "흙": 1272, + "흠": 1273, + "흡": 1274, + "흥": 1275, + "흩": 1276, + "희": 1277, + "흰": 1278, + "히": 1279, + "힌": 1280, + "힐": 1281, + "힘": 1282 +}