Upload tokenizer

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 835,
+  "<s>": 834
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "832": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "833": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "834": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "835": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,836 @@
+{
+  "(": 1,
+  ")": 2,
+  ":": 3,
+  "N": 4,
+  "P": 5,
+  "S": 6,
+  "[PAD]": 833,
+  "[UNK]": 832,
+  "|": 0,
+  "가": 7,
+  "각": 8,
+  "간": 9,
+  "갇": 10,
+  "갈": 11,
+  "갉": 12,
+  "감": 13,
+  "갑": 14,
+  "값": 15,
+  "갓": 16,
+  "갔": 17,
+  "강": 18,
+  "갖": 19,
+  "같": 20,
+  "개": 21,
+  "객": 22,
+  "갱": 23,
+  "걔": 24,
+  "거": 25,
+  "걱": 26,
+  "건": 27,
+  "걸": 28,
+  "검": 29,
+  "겁": 30,
+  "것": 31,
+  "게": 32,
+  "겟": 33,
+  "겠": 34,
+  "겨": 35,
+  "격": 36,
+  "겪": 37,
+  "견": 38,
+  "결": 39,
+  "겸": 40,
+  "겹": 41,
+  "겼": 42,
+  "경": 43,
+  "계": 44,
+  "고": 45,
+  "곤": 46,
+  "곧": 47,
+  "골": 48,
+  "곰": 49,
+  "곱": 50,
+  "곳": 51,
+  "공": 52,
+  "곶": 53,
+  "과": 54,
+  "관": 55,
+  "광": 56,
+  "괜": 57,
+  "괴": 58,
+  "굉": 59,
+  "교": 60,
+  "구": 61,
+  "국": 62,
+  "군": 63,
+  "굳": 64,
+  "굴": 65,
+  "굵": 66,
+  "굽": 67,
+  "궁": 68,
+  "권": 69,
+  "귀": 70,
+  "규": 71,
+  "균": 72,
+  "그": 73,
+  "극": 74,
+  "근": 75,
+  "글": 76,
+  "금": 77,
+  "급": 78,
+  "긍": 79,
+  "기": 80,
+  "긴": 81,
+  "길": 82,
+  "김": 83,
+  "깊": 84,
+  "까": 85,
+  "깍": 86,
+  "깐": 87,
+  "깜": 88,
+  "깝": 89,
+  "깨": 90,
+  "깼": 91,
+  "꺼": 92,
+  "꺽": 93,
+  "께": 94,
+  "껴": 95,
+  "꼈": 96,
+  "꼬": 97,
+  "꼭": 98,
+  "꽁": 99,
+  "꽃": 100,
+  "꽤": 101,
+  "꾸": 102,
+  "꿀": 103,
+  "꿈": 104,
+  "꿍": 105,
+  "꿔": 106,
+  "뀌": 107,
+  "뀐": 108,
+  "끄": 109,
+  "끊": 110,
+  "끌": 111,
+  "끓": 112,
+  "끔": 113,
+  "끗": 114,
+  "끝": 115,
+  "끼": 116,
+  "끽": 117,
+  "낀": 118,
+  "낌": 119,
+  "나": 120,
+  "낙": 121,
+  "낚": 122,
+  "난": 123,
+  "날": 124,
+  "낡": 125,
+  "남": 126,
+  "낫": 127,
+  "났": 128,
+  "낭": 129,
+  "낮": 130,
+  "내": 131,
+  "낸": 132,
+  "낼": 133,
+  "냄": 134,
+  "냈": 135,
+  "냐": 136,
+  "냥": 137,
+  "너": 138,
+  "넓": 139,
+  "넘": 140,
+  "넣": 141,
+  "네": 142,
+  "넷": 143,
+  "녀": 144,
+  "녁": 145,
+  "년": 146,
+  "념": 147,
+  "녔": 148,
+  "노": 149,
+  "녹": 150,
+  "논": 151,
+  "놀": 152,
+  "놈": 153,
+  "높": 154,
+  "놓": 155,
+  "놔": 156,
+  "놨": 157,
+  "누": 158,
+  "눈": 159,
+  "눠": 160,
+  "뉴": 161,
+  "느": 162,
+  "는": 163,
+  "늘": 164,
+  "늙": 165,
+  "능": 166,
+  "늦": 167,
+  "늬": 168,
+  "니": 169,
+  "닌": 170,
+  "닐": 171,
+  "님": 172,
+  "다": 173,
+  "닥": 174,
+  "단": 175,
+  "닫": 176,
+  "달": 177,
+  "닭": 178,
+  "담": 179,
+  "답": 180,
+  "닷": 181,
+  "당": 182,
+  "닿": 183,
+  "대": 184,
+  "댁": 185,
+  "댐": 186,
+  "더": 187,
+  "던": 188,
+  "덟": 189,
+  "덤": 190,
+  "덥": 191,
+  "덩": 192,
+  "데": 193,
+  "덴": 194,
+  "델": 195,
+  "도": 196,
+  "독": 197,
+  "돈": 198,
+  "돌": 199,
+  "동": 200,
+  "돼": 201,
+  "됐": 202,
+  "되": 203,
+  "된": 204,
+  "될": 205,
+  "두": 206,
+  "둑": 207,
+  "둘": 208,
+  "둡": 209,
+  "둬": 210,
+  "뒤": 211,
+  "뒷": 212,
+  "드": 213,
+  "득": 214,
+  "든": 215,
+  "듣": 216,
+  "들": 217,
+  "듯": 218,
+  "등": 219,
+  "디": 220,
+  "딘": 221,
+  "딩": 222,
+  "딪": 223,
+  "따": 224,
+  "딱": 225,
+  "딸": 226,
+  "땅": 227,
+  "때": 228,
+  "땐": 229,
+  "떠": 230,
+  "떤": 231,
+  "떨": 232,
+  "떻": 233,
+  "또": 234,
+  "똑": 235,
+  "뛰": 236,
+  "뜩": 237,
+  "뜰": 238,
+  "뜻": 239,
+  "띄": 240,
+  "띠": 241,
+  "라": 242,
+  "락": 243,
+  "란": 244,
+  "랄": 245,
+  "람": 246,
+  "랏": 247,
+  "랐": 248,
+  "랑": 249,
+  "래": 250,
+  "랜": 251,
+  "램": 252,
+  "랬": 253,
+  "량": 254,
+  "러": 255,
+  "런": 256,
+  "럴": 257,
+  "럼": 258,
+  "럽": 259,
+  "렇": 260,
+  "레": 261,
+  "렉": 262,
+  "렌": 263,
+  "려": 264,
+  "력": 265,
+  "련": 266,
+  "렴": 267,
+  "렵": 268,
+  "렸": 269,
+  "령": 270,
+  "례": 271,
+  "로": 272,
+  "록": 273,
+  "론": 274,
+  "롭": 275,
+  "롯": 276,
+  "롱": 277,
+  "뢰": 278,
+  "료": 279,
+  "루": 280,
+  "룬": 281,
+  "룸": 282,
+  "류": 283,
+  "륙": 284,
+  "률": 285,
+  "르": 286,
+  "른": 287,
+  "를": 288,
+  "름": 289,
+  "릉": 290,
+  "리": 291,
+  "린": 292,
+  "릴": 293,
+  "림": 294,
+  "립": 295,
+  "릿": 296,
+  "링": 297,
+  "마": 298,
+  "막": 299,
+  "만": 300,
+  "많": 301,
+  "말": 302,
+  "맑": 303,
+  "맘": 304,
+  "맙": 305,
+  "맛": 306,
+  "망": 307,
+  "맞": 308,
+  "매": 309,
+  "맥": 310,
+  "맨": 311,
+  "맹": 312,
+  "머": 313,
+  "먹": 314,
+  "먼": 315,
+  "멈": 316,
+  "멋": 317,
+  "메": 318,
+  "멧": 319,
+  "며": 320,
+  "면": 321,
+  "명": 322,
+  "몇": 323,
+  "모": 324,
+  "목": 325,
+  "몬": 326,
+  "몰": 327,
+  "몸": 328,
+  "못": 329,
+  "묘": 330,
+  "무": 331,
+  "묵": 332,
+  "문": 333,
+  "물": 334,
+  "뭐": 335,
+  "뭔": 336,
+  "뭘": 337,
+  "뮤": 338,
+  "미": 339,
+  "믹": 340,
+  "민": 341,
+  "믿": 342,
+  "밀": 343,
+  "밌": 344,
+  "밍": 345,
+  "밑": 346,
+  "바": 347,
+  "박": 348,
+  "밖": 349,
+  "반": 350,
+  "받": 351,
+  "발": 352,
+  "밝": 353,
+  "밤": 354,
+  "밥": 355,
+  "방": 356,
+  "밭": 357,
+  "배": 358,
+  "백": 359,
+  "버": 360,
+  "벅": 361,
+  "번": 362,
+  "벌": 363,
+  "법": 364,
+  "베": 365,
+  "벤": 366,
+  "벼": 367,
+  "벽": 368,
+  "변": 369,
+  "별": 370,
+  "볍": 371,
+  "병": 372,
+  "보": 373,
+  "복": 374,
+  "볶": 375,
+  "본": 376,
+  "볼": 377,
+  "봇": 378,
+  "봉": 379,
+  "봐": 380,
+  "봤": 381,
+  "부": 382,
+  "북": 383,
+  "분": 384,
+  "불": 385,
+  "붓": 386,
+  "붕": 387,
+  "붙": 388,
+  "브": 389,
+  "블": 390,
+  "비": 391,
+  "빌": 392,
+  "빛": 393,
+  "빠": 394,
+  "빡": 395,
+  "빨": 396,
+  "빼": 397,
+  "빽": 398,
+  "뻐": 399,
+  "뻔": 400,
+  "뽑": 401,
+  "뿌": 402,
+  "뿐": 403,
+  "쁘": 404,
+  "쁜": 405,
+  "사": 406,
+  "산": 407,
+  "살": 408,
+  "삶": 409,
+  "삼": 410,
+  "샀": 411,
+  "상": 412,
+  "새": 413,
+  "색": 414,
+  "생": 415,
+  "샵": 416,
+  "서": 417,
+  "석": 418,
+  "섞": 419,
+  "선": 420,
+  "설": 421,
+  "섬": 422,
+  "섭": 423,
+  "섯": 424,
+  "성": 425,
+  "세": 426,
+  "센": 427,
+  "셔": 428,
+  "션": 429,
+  "셨": 430,
+  "셰": 431,
+  "소": 432,
+  "속": 433,
+  "손": 434,
+  "솔": 435,
+  "솜": 436,
+  "송": 437,
+  "쇄": 438,
+  "쇠": 439,
+  "쇼": 440,
+  "숍": 441,
+  "수": 442,
+  "숙": 443,
+  "순": 444,
+  "술": 445,
+  "숨": 446,
+  "쉐": 447,
+  "쉬": 448,
+  "쉽": 449,
+  "스": 450,
+  "슨": 451,
+  "슬": 452,
+  "습": 453,
+  "슷": 454,
+  "시": 455,
+  "식": 456,
+  "신": 457,
+  "실": 458,
+  "싫": 459,
+  "심": 460,
+  "십": 461,
+  "싱": 462,
+  "싶": 463,
+  "싸": 464,
+  "싹": 465,
+  "싼": 466,
+  "쌤": 467,
+  "써": 468,
+  "썩": 469,
+  "썼": 470,
+  "쎄": 471,
+  "쏟": 472,
+  "쓰": 473,
+  "쓴": 474,
+  "쓸": 475,
+  "씨": 476,
+  "씩": 477,
+  "씬": 478,
+  "씹": 479,
+  "씻": 480,
+  "아": 481,
+  "악": 482,
+  "안": 483,
+  "앉": 484,
+  "않": 485,
+  "알": 486,
+  "앓": 487,
+  "암": 488,
+  "압": 489,
+  "았": 490,
+  "앞": 491,
+  "애": 492,
+  "액": 493,
+  "앤": 494,
+  "야": 495,
+  "약": 496,
+  "얇": 497,
+  "양": 498,
+  "얘": 499,
+  "어": 500,
+  "억": 501,
+  "언": 502,
+  "얻": 503,
+  "얼": 504,
+  "엄": 505,
+  "업": 506,
+  "없": 507,
+  "었": 508,
+  "엉": 509,
+  "엊": 510,
+  "엎": 511,
+  "에": 512,
+  "엔": 513,
+  "엘": 514,
+  "여": 515,
+  "역": 516,
+  "연": 517,
+  "열": 518,
+  "염": 519,
+  "엽": 520,
+  "였": 521,
+  "영": 522,
+  "옆": 523,
+  "예": 524,
+  "옛": 525,
+  "오": 526,
+  "옥": 527,
+  "온": 528,
+  "올": 529,
+  "옷": 530,
+  "와": 531,
+  "완": 532,
+  "왓": 533,
+  "왔": 534,
+  "왕": 535,
+  "왜": 536,
+  "외": 537,
+  "요": 538,
+  "욕": 539,
+  "용": 540,
+  "우": 541,
+  "욱": 542,
+  "운": 543,
+  "울": 544,
+  "움": 545,
+  "웃": 546,
+  "웅": 547,
+  "워": 548,
+  "원": 549,
+  "월": 550,
+  "웠": 551,
+  "웨": 552,
+  "웬": 553,
+  "위": 554,
+  "유": 555,
+  "육": 556,
+  "율": 557,
+  "으": 558,
+  "은": 559,
+  "을": 560,
+  "음": 561,
+  "응": 562,
+  "의": 563,
+  "이": 564,
+  "익": 565,
+  "인": 566,
+  "일": 567,
+  "읽": 568,
+  "임": 569,
+  "입": 570,
+  "잇": 571,
+  "있": 572,
+  "잊": 573,
+  "잎": 574,
+  "자": 575,
+  "작": 576,
+  "잔": 577,
+  "잖": 578,
+  "잘": 579,
+  "잠": 580,
+  "잡": 581,
+  "잣": 582,
+  "장": 583,
+  "재": 584,
+  "쟁": 585,
+  "저": 586,
+  "적": 587,
+  "전": 588,
+  "절": 589,
+  "젊": 590,
+  "점": 591,
+  "접": 592,
+  "정": 593,
+  "젖": 594,
+  "제": 595,
+  "져": 596,
+  "졌": 597,
+  "조": 598,
+  "족": 599,
+  "존": 600,
+  "졸": 601,
+  "좀": 602,
+  "좁": 603,
+  "종": 604,
+  "좋": 605,
+  "좌": 606,
+  "죠": 607,
+  "주": 608,
+  "죽": 609,
+  "준": 610,
+  "줄": 611,
+  "줌": 612,
+  "중": 613,
+  "줘": 614,
+  "줬": 615,
+  "쥐": 616,
+  "즈": 617,
+  "즐": 618,
+  "즘": 619,
+  "즙": 620,
+  "증": 621,
+  "지": 622,
+  "직": 623,
+  "진": 624,
+  "질": 625,
+  "집": 626,
+  "짓": 627,
+  "징": 628,
+  "짜": 629,
+  "짝": 630,
+  "짧": 631,
+  "째": 632,
+  "쨌": 633,
+  "쩔": 634,
+  "쪄": 635,
+  "쪼": 636,
+  "쪽": 637,
+  "쫄": 638,
+  "쫌": 639,
+  "쫙": 640,
+  "쭉": 641,
+  "쯤": 642,
+  "찌": 643,
+  "찍": 644,
+  "찐": 645,
+  "찜": 646,
+  "찝": 647,
+  "차": 648,
+  "착": 649,
+  "찬": 650,
+  "찮": 651,
+  "찰": 652,
+  "참": 653,
+  "찻": 654,
+  "창": 655,
+  "찾": 656,
+  "채": 657,
+  "책": 658,
+  "챙": 659,
+  "처": 660,
+  "척": 661,
+  "천": 662,
+  "철": 663,
+  "첨": 664,
+  "첫": 665,
+  "청": 666,
+  "체": 667,
+  "쳐": 668,
+  "쳤": 669,
+  "초": 670,
+  "총": 671,
+  "촬": 672,
+  "최": 673,
+  "추": 674,
+  "축": 675,
+  "춘": 676,
+  "출": 677,
+  "춥": 678,
+  "춧": 679,
+  "충": 680,
+  "춰": 681,
+  "췄": 682,
+  "취": 683,
+  "층": 684,
+  "치": 685,
+  "칙": 686,
+  "친": 687,
+  "칠": 688,
+  "칡": 689,
+  "침": 690,
+  "칫": 691,
+  "칭": 692,
+  "카": 693,
+  "캉": 694,
+  "캠": 695,
+  "커": 696,
+  "컨": 697,
+  "컬": 698,
+  "컴": 699,
+  "컸": 700,
+  "케": 701,
+  "켓": 702,
+  "켜": 703,
+  "코": 704,
+  "콕": 705,
+  "콘": 706,
+  "콜": 707,
+  "콩": 708,
+  "쾌": 709,
+  "크": 710,
+  "큰": 711,
+  "클": 712,
+  "큼": 713,
+  "키": 714,
+  "킨": 715,
+  "킹": 716,
+  "타": 717,
+  "탁": 718,
+  "탄": 719,
+  "탈": 720,
+  "탔": 721,
+  "탕": 722,
+  "태": 723,
+  "택": 724,
+  "터": 725,
+  "턴": 726,
+  "털": 727,
+  "텃": 728,
+  "테": 729,
+  "텍": 730,
+  "텐": 731,
+  "텔": 732,
+  "템": 733,
+  "토": 734,
+  "톡": 735,
+  "통": 736,
+  "퇴": 737,
+  "투": 738,
+  "툭": 739,
+  "퉁": 740,
+  "튀": 741,
+  "튈": 742,
+  "튜": 743,
+  "트": 744,
+  "특": 745,
+  "튼": 746,
+  "틀": 747,
+  "티": 748,
+  "틱": 749,
+  "틴": 750,
+  "팀": 751,
+  "팅": 752,
+  "파": 753,
+  "팍": 754,
+  "판": 755,
+  "팔": 756,
+  "팠": 757,
+  "패": 758,
+  "팰": 759,
+  "퍼": 760,
+  "페": 761,
+  "펜": 762,
+  "편": 763,
+  "평": 764,
+  "폐": 765,
+  "포": 766,
+  "폰": 767,
+  "폼": 768,
+  "표": 769,
+  "푸": 770,
+  "품": 771,
+  "풍": 772,
+  "퓨": 773,
+  "프": 774,
+  "픈": 775,
+  "플": 776,
+  "피": 777,
+  "필": 778,
+  "핑": 779,
+  "하": 780,
+  "학": 781,
+  "한": 782,
+  "할": 783,
+  "함": 784,
+  "합": 785,
+  "핫": 786,
+  "항": 787,
+  "해": 788,
+  "핸": 789,
+  "햇": 790,
+  "했": 791,
+  "행": 792,
+  "향": 793,
+  "허": 794,
+  "헐": 795,
+  "험": 796,
+  "헤": 797,
+  "헬": 798,
+  "혀": 799,
+  "현": 800,
+  "혈": 801,
+  "협": 802,
+  "형": 803,
+  "호": 804,
+  "혹": 805,
+  "혼": 806,
+  "홈": 807,
+  "홍": 808,
+  "화": 809,
+  "확": 810,
+  "환": 811,
+  "활": 812,
+  "황": 813,
+  "회": 814,
+  "획": 815,
+  "효": 816,
+  "후": 817,
+  "훨": 818,
+  "휙": 819,
+  "휴": 820,
+  "흐": 821,
+  "흔": 822,
+  "흘": 823,
+  "흙": 824,
+  "흥": 825,
+  "흩": 826,
+  "희": 827,
+  "히": 828,
+  "힌": 829,
+  "힐": 830,
+  "힘": 831
+}