Upload tokenizer
463f0a7
verified
|
{ |
|
"(": 1, |
|
")": 2, |
|
"[PAD]": 832, |
|
"[UNK]": 831, |
|
"n": 3, |
|
"p": 4, |
|
"s": 5, |
|
"|": 0, |
|
"가": 6, |
|
"각": 7, |
|
"간": 8, |
|
"갇": 9, |
|
"갈": 10, |
|
"갉": 11, |
|
"감": 12, |
|
"갑": 13, |
|
"값": 14, |
|
"갓": 15, |
|
"갔": 16, |
|
"강": 17, |
|
"갖": 18, |
|
"같": 19, |
|
"개": 20, |
|
"객": 21, |
|
"갱": 22, |
|
"걔": 23, |
|
"거": 24, |
|
"걱": 25, |
|
"건": 26, |
|
"걸": 27, |
|
"검": 28, |
|
"겁": 29, |
|
"것": 30, |
|
"게": 31, |
|
"겟": 32, |
|
"겠": 33, |
|
"겨": 34, |
|
"격": 35, |
|
"겪": 36, |
|
"견": 37, |
|
"결": 38, |
|
"겸": 39, |
|
"겹": 40, |
|
"겼": 41, |
|
"경": 42, |
|
"계": 43, |
|
"고": 44, |
|
"곤": 45, |
|
"곧": 46, |
|
"골": 47, |
|
"곰": 48, |
|
"곱": 49, |
|
"곳": 50, |
|
"공": 51, |
|
"곶": 52, |
|
"과": 53, |
|
"관": 54, |
|
"광": 55, |
|
"괜": 56, |
|
"괴": 57, |
|
"굉": 58, |
|
"교": 59, |
|
"구": 60, |
|
"국": 61, |
|
"군": 62, |
|
"굳": 63, |
|
"굴": 64, |
|
"굵": 65, |
|
"굽": 66, |
|
"궁": 67, |
|
"권": 68, |
|
"귀": 69, |
|
"규": 70, |
|
"균": 71, |
|
"그": 72, |
|
"극": 73, |
|
"근": 74, |
|
"글": 75, |
|
"금": 76, |
|
"급": 77, |
|
"긍": 78, |
|
"기": 79, |
|
"긴": 80, |
|
"길": 81, |
|
"김": 82, |
|
"깊": 83, |
|
"까": 84, |
|
"깍": 85, |
|
"깐": 86, |
|
"깜": 87, |
|
"깝": 88, |
|
"깨": 89, |
|
"깼": 90, |
|
"꺼": 91, |
|
"꺽": 92, |
|
"께": 93, |
|
"껴": 94, |
|
"꼈": 95, |
|
"꼬": 96, |
|
"꼭": 97, |
|
"꽁": 98, |
|
"꽃": 99, |
|
"꽤": 100, |
|
"꾸": 101, |
|
"꿀": 102, |
|
"꿈": 103, |
|
"꿍": 104, |
|
"꿔": 105, |
|
"뀌": 106, |
|
"뀐": 107, |
|
"끄": 108, |
|
"끊": 109, |
|
"끌": 110, |
|
"끓": 111, |
|
"끔": 112, |
|
"끗": 113, |
|
"끝": 114, |
|
"끼": 115, |
|
"끽": 116, |
|
"낀": 117, |
|
"낌": 118, |
|
"나": 119, |
|
"낙": 120, |
|
"낚": 121, |
|
"난": 122, |
|
"날": 123, |
|
"낡": 124, |
|
"남": 125, |
|
"낫": 126, |
|
"났": 127, |
|
"낭": 128, |
|
"낮": 129, |
|
"내": 130, |
|
"낸": 131, |
|
"낼": 132, |
|
"냄": 133, |
|
"냈": 134, |
|
"냐": 135, |
|
"냥": 136, |
|
"너": 137, |
|
"넓": 138, |
|
"넘": 139, |
|
"넣": 140, |
|
"네": 141, |
|
"넷": 142, |
|
"녀": 143, |
|
"녁": 144, |
|
"년": 145, |
|
"념": 146, |
|
"녔": 147, |
|
"노": 148, |
|
"녹": 149, |
|
"논": 150, |
|
"놀": 151, |
|
"놈": 152, |
|
"높": 153, |
|
"놓": 154, |
|
"놔": 155, |
|
"놨": 156, |
|
"누": 157, |
|
"눈": 158, |
|
"눠": 159, |
|
"뉴": 160, |
|
"느": 161, |
|
"는": 162, |
|
"늘": 163, |
|
"늙": 164, |
|
"능": 165, |
|
"늦": 166, |
|
"늬": 167, |
|
"니": 168, |
|
"닌": 169, |
|
"닐": 170, |
|
"님": 171, |
|
"다": 172, |
|
"닥": 173, |
|
"단": 174, |
|
"닫": 175, |
|
"달": 176, |
|
"닭": 177, |
|
"담": 178, |
|
"답": 179, |
|
"닷": 180, |
|
"당": 181, |
|
"닿": 182, |
|
"대": 183, |
|
"댁": 184, |
|
"댐": 185, |
|
"더": 186, |
|
"던": 187, |
|
"덟": 188, |
|
"덤": 189, |
|
"덥": 190, |
|
"덩": 191, |
|
"데": 192, |
|
"덴": 193, |
|
"델": 194, |
|
"도": 195, |
|
"독": 196, |
|
"돈": 197, |
|
"돌": 198, |
|
"동": 199, |
|
"돼": 200, |
|
"됐": 201, |
|
"되": 202, |
|
"된": 203, |
|
"될": 204, |
|
"두": 205, |
|
"둑": 206, |
|
"둘": 207, |
|
"둡": 208, |
|
"둬": 209, |
|
"뒤": 210, |
|
"뒷": 211, |
|
"드": 212, |
|
"득": 213, |
|
"든": 214, |
|
"듣": 215, |
|
"들": 216, |
|
"듯": 217, |
|
"등": 218, |
|
"디": 219, |
|
"딘": 220, |
|
"딩": 221, |
|
"딪": 222, |
|
"따": 223, |
|
"딱": 224, |
|
"딸": 225, |
|
"땅": 226, |
|
"때": 227, |
|
"땐": 228, |
|
"떠": 229, |
|
"떤": 230, |
|
"떨": 231, |
|
"떻": 232, |
|
"또": 233, |
|
"똑": 234, |
|
"뛰": 235, |
|
"뜩": 236, |
|
"뜰": 237, |
|
"뜻": 238, |
|
"띄": 239, |
|
"띠": 240, |
|
"라": 241, |
|
"락": 242, |
|
"란": 243, |
|
"랄": 244, |
|
"람": 245, |
|
"랏": 246, |
|
"랐": 247, |
|
"랑": 248, |
|
"래": 249, |
|
"랜": 250, |
|
"램": 251, |
|
"랬": 252, |
|
"량": 253, |
|
"러": 254, |
|
"런": 255, |
|
"럴": 256, |
|
"럼": 257, |
|
"럽": 258, |
|
"렇": 259, |
|
"레": 260, |
|
"렉": 261, |
|
"렌": 262, |
|
"려": 263, |
|
"력": 264, |
|
"련": 265, |
|
"렴": 266, |
|
"렵": 267, |
|
"렸": 268, |
|
"령": 269, |
|
"례": 270, |
|
"로": 271, |
|
"록": 272, |
|
"론": 273, |
|
"롭": 274, |
|
"롯": 275, |
|
"롱": 276, |
|
"뢰": 277, |
|
"료": 278, |
|
"루": 279, |
|
"룬": 280, |
|
"룸": 281, |
|
"류": 282, |
|
"륙": 283, |
|
"률": 284, |
|
"르": 285, |
|
"른": 286, |
|
"를": 287, |
|
"름": 288, |
|
"릉": 289, |
|
"리": 290, |
|
"린": 291, |
|
"릴": 292, |
|
"림": 293, |
|
"립": 294, |
|
"릿": 295, |
|
"링": 296, |
|
"마": 297, |
|
"막": 298, |
|
"만": 299, |
|
"많": 300, |
|
"말": 301, |
|
"맑": 302, |
|
"맘": 303, |
|
"맙": 304, |
|
"맛": 305, |
|
"망": 306, |
|
"맞": 307, |
|
"매": 308, |
|
"맥": 309, |
|
"맨": 310, |
|
"맹": 311, |
|
"머": 312, |
|
"먹": 313, |
|
"먼": 314, |
|
"멈": 315, |
|
"멋": 316, |
|
"메": 317, |
|
"멧": 318, |
|
"며": 319, |
|
"면": 320, |
|
"명": 321, |
|
"몇": 322, |
|
"모": 323, |
|
"목": 324, |
|
"몬": 325, |
|
"몰": 326, |
|
"몸": 327, |
|
"못": 328, |
|
"묘": 329, |
|
"무": 330, |
|
"묵": 331, |
|
"문": 332, |
|
"물": 333, |
|
"뭐": 334, |
|
"뭔": 335, |
|
"뭘": 336, |
|
"뮤": 337, |
|
"미": 338, |
|
"믹": 339, |
|
"민": 340, |
|
"믿": 341, |
|
"밀": 342, |
|
"밌": 343, |
|
"밍": 344, |
|
"밑": 345, |
|
"바": 346, |
|
"박": 347, |
|
"밖": 348, |
|
"반": 349, |
|
"받": 350, |
|
"발": 351, |
|
"밝": 352, |
|
"밤": 353, |
|
"밥": 354, |
|
"방": 355, |
|
"밭": 356, |
|
"배": 357, |
|
"백": 358, |
|
"버": 359, |
|
"벅": 360, |
|
"번": 361, |
|
"벌": 362, |
|
"법": 363, |
|
"베": 364, |
|
"벤": 365, |
|
"벼": 366, |
|
"벽": 367, |
|
"변": 368, |
|
"별": 369, |
|
"볍": 370, |
|
"병": 371, |
|
"보": 372, |
|
"복": 373, |
|
"볶": 374, |
|
"본": 375, |
|
"볼": 376, |
|
"봇": 377, |
|
"봉": 378, |
|
"봐": 379, |
|
"봤": 380, |
|
"부": 381, |
|
"북": 382, |
|
"분": 383, |
|
"불": 384, |
|
"붓": 385, |
|
"붕": 386, |
|
"붙": 387, |
|
"브": 388, |
|
"블": 389, |
|
"비": 390, |
|
"빌": 391, |
|
"빛": 392, |
|
"빠": 393, |
|
"빡": 394, |
|
"빨": 395, |
|
"빼": 396, |
|
"빽": 397, |
|
"뻐": 398, |
|
"뻔": 399, |
|
"뽑": 400, |
|
"뿌": 401, |
|
"뿐": 402, |
|
"쁘": 403, |
|
"쁜": 404, |
|
"사": 405, |
|
"산": 406, |
|
"살": 407, |
|
"삶": 408, |
|
"삼": 409, |
|
"샀": 410, |
|
"상": 411, |
|
"새": 412, |
|
"색": 413, |
|
"생": 414, |
|
"샵": 415, |
|
"서": 416, |
|
"석": 417, |
|
"섞": 418, |
|
"선": 419, |
|
"설": 420, |
|
"섬": 421, |
|
"섭": 422, |
|
"섯": 423, |
|
"성": 424, |
|
"세": 425, |
|
"센": 426, |
|
"셔": 427, |
|
"션": 428, |
|
"셨": 429, |
|
"셰": 430, |
|
"소": 431, |
|
"속": 432, |
|
"손": 433, |
|
"솔": 434, |
|
"솜": 435, |
|
"송": 436, |
|
"쇄": 437, |
|
"쇠": 438, |
|
"쇼": 439, |
|
"숍": 440, |
|
"수": 441, |
|
"숙": 442, |
|
"순": 443, |
|
"술": 444, |
|
"숨": 445, |
|
"쉐": 446, |
|
"쉬": 447, |
|
"쉽": 448, |
|
"스": 449, |
|
"슨": 450, |
|
"슬": 451, |
|
"습": 452, |
|
"슷": 453, |
|
"시": 454, |
|
"식": 455, |
|
"신": 456, |
|
"실": 457, |
|
"싫": 458, |
|
"심": 459, |
|
"십": 460, |
|
"싱": 461, |
|
"싶": 462, |
|
"싸": 463, |
|
"싹": 464, |
|
"싼": 465, |
|
"쌤": 466, |
|
"써": 467, |
|
"썩": 468, |
|
"썼": 469, |
|
"쎄": 470, |
|
"쏟": 471, |
|
"쓰": 472, |
|
"쓴": 473, |
|
"쓸": 474, |
|
"씨": 475, |
|
"씩": 476, |
|
"씬": 477, |
|
"씹": 478, |
|
"씻": 479, |
|
"아": 480, |
|
"악": 481, |
|
"안": 482, |
|
"앉": 483, |
|
"않": 484, |
|
"알": 485, |
|
"앓": 486, |
|
"암": 487, |
|
"압": 488, |
|
"았": 489, |
|
"앞": 490, |
|
"애": 491, |
|
"액": 492, |
|
"앤": 493, |
|
"야": 494, |
|
"약": 495, |
|
"얇": 496, |
|
"양": 497, |
|
"얘": 498, |
|
"어": 499, |
|
"억": 500, |
|
"언": 501, |
|
"얻": 502, |
|
"얼": 503, |
|
"엄": 504, |
|
"업": 505, |
|
"없": 506, |
|
"었": 507, |
|
"엉": 508, |
|
"엊": 509, |
|
"엎": 510, |
|
"에": 511, |
|
"엔": 512, |
|
"엘": 513, |
|
"여": 514, |
|
"역": 515, |
|
"연": 516, |
|
"열": 517, |
|
"염": 518, |
|
"엽": 519, |
|
"였": 520, |
|
"영": 521, |
|
"옆": 522, |
|
"예": 523, |
|
"옛": 524, |
|
"오": 525, |
|
"옥": 526, |
|
"온": 527, |
|
"올": 528, |
|
"옷": 529, |
|
"와": 530, |
|
"완": 531, |
|
"왓": 532, |
|
"왔": 533, |
|
"왕": 534, |
|
"왜": 535, |
|
"외": 536, |
|
"요": 537, |
|
"욕": 538, |
|
"용": 539, |
|
"우": 540, |
|
"욱": 541, |
|
"운": 542, |
|
"울": 543, |
|
"움": 544, |
|
"웃": 545, |
|
"웅": 546, |
|
"워": 547, |
|
"원": 548, |
|
"월": 549, |
|
"웠": 550, |
|
"웨": 551, |
|
"웬": 552, |
|
"위": 553, |
|
"유": 554, |
|
"육": 555, |
|
"율": 556, |
|
"으": 557, |
|
"은": 558, |
|
"을": 559, |
|
"음": 560, |
|
"응": 561, |
|
"의": 562, |
|
"이": 563, |
|
"익": 564, |
|
"인": 565, |
|
"일": 566, |
|
"읽": 567, |
|
"임": 568, |
|
"입": 569, |
|
"잇": 570, |
|
"있": 571, |
|
"잊": 572, |
|
"잎": 573, |
|
"자": 574, |
|
"작": 575, |
|
"잔": 576, |
|
"잖": 577, |
|
"잘": 578, |
|
"잠": 579, |
|
"잡": 580, |
|
"잣": 581, |
|
"장": 582, |
|
"재": 583, |
|
"쟁": 584, |
|
"저": 585, |
|
"적": 586, |
|
"전": 587, |
|
"절": 588, |
|
"젊": 589, |
|
"점": 590, |
|
"접": 591, |
|
"정": 592, |
|
"젖": 593, |
|
"제": 594, |
|
"져": 595, |
|
"졌": 596, |
|
"조": 597, |
|
"족": 598, |
|
"존": 599, |
|
"졸": 600, |
|
"좀": 601, |
|
"좁": 602, |
|
"종": 603, |
|
"좋": 604, |
|
"좌": 605, |
|
"죠": 606, |
|
"주": 607, |
|
"죽": 608, |
|
"준": 609, |
|
"줄": 610, |
|
"줌": 611, |
|
"중": 612, |
|
"줘": 613, |
|
"줬": 614, |
|
"쥐": 615, |
|
"즈": 616, |
|
"즐": 617, |
|
"즘": 618, |
|
"즙": 619, |
|
"증": 620, |
|
"지": 621, |
|
"직": 622, |
|
"진": 623, |
|
"질": 624, |
|
"집": 625, |
|
"짓": 626, |
|
"징": 627, |
|
"짜": 628, |
|
"짝": 629, |
|
"짧": 630, |
|
"째": 631, |
|
"쨌": 632, |
|
"쩔": 633, |
|
"쪄": 634, |
|
"쪼": 635, |
|
"쪽": 636, |
|
"쫄": 637, |
|
"쫌": 638, |
|
"쫙": 639, |
|
"쭉": 640, |
|
"쯤": 641, |
|
"찌": 642, |
|
"찍": 643, |
|
"찐": 644, |
|
"찜": 645, |
|
"찝": 646, |
|
"차": 647, |
|
"착": 648, |
|
"찬": 649, |
|
"찮": 650, |
|
"찰": 651, |
|
"참": 652, |
|
"찻": 653, |
|
"창": 654, |
|
"찾": 655, |
|
"채": 656, |
|
"책": 657, |
|
"챙": 658, |
|
"처": 659, |
|
"척": 660, |
|
"천": 661, |
|
"철": 662, |
|
"첨": 663, |
|
"첫": 664, |
|
"청": 665, |
|
"체": 666, |
|
"쳐": 667, |
|
"쳤": 668, |
|
"초": 669, |
|
"총": 670, |
|
"촬": 671, |
|
"최": 672, |
|
"추": 673, |
|
"축": 674, |
|
"춘": 675, |
|
"출": 676, |
|
"춥": 677, |
|
"춧": 678, |
|
"충": 679, |
|
"춰": 680, |
|
"췄": 681, |
|
"취": 682, |
|
"층": 683, |
|
"치": 684, |
|
"칙": 685, |
|
"친": 686, |
|
"칠": 687, |
|
"칡": 688, |
|
"침": 689, |
|
"칫": 690, |
|
"칭": 691, |
|
"카": 692, |
|
"캉": 693, |
|
"캠": 694, |
|
"커": 695, |
|
"컨": 696, |
|
"컬": 697, |
|
"컴": 698, |
|
"컸": 699, |
|
"케": 700, |
|
"켓": 701, |
|
"켜": 702, |
|
"코": 703, |
|
"콕": 704, |
|
"콘": 705, |
|
"콜": 706, |
|
"콩": 707, |
|
"쾌": 708, |
|
"크": 709, |
|
"큰": 710, |
|
"클": 711, |
|
"큼": 712, |
|
"키": 713, |
|
"킨": 714, |
|
"킹": 715, |
|
"타": 716, |
|
"탁": 717, |
|
"탄": 718, |
|
"탈": 719, |
|
"탔": 720, |
|
"탕": 721, |
|
"태": 722, |
|
"택": 723, |
|
"터": 724, |
|
"턴": 725, |
|
"털": 726, |
|
"텃": 727, |
|
"테": 728, |
|
"텍": 729, |
|
"텐": 730, |
|
"텔": 731, |
|
"템": 732, |
|
"토": 733, |
|
"톡": 734, |
|
"통": 735, |
|
"퇴": 736, |
|
"투": 737, |
|
"툭": 738, |
|
"퉁": 739, |
|
"튀": 740, |
|
"튈": 741, |
|
"튜": 742, |
|
"트": 743, |
|
"특": 744, |
|
"튼": 745, |
|
"틀": 746, |
|
"티": 747, |
|
"틱": 748, |
|
"틴": 749, |
|
"팀": 750, |
|
"팅": 751, |
|
"파": 752, |
|
"팍": 753, |
|
"판": 754, |
|
"팔": 755, |
|
"팠": 756, |
|
"패": 757, |
|
"팰": 758, |
|
"퍼": 759, |
|
"페": 760, |
|
"펜": 761, |
|
"편": 762, |
|
"평": 763, |
|
"폐": 764, |
|
"포": 765, |
|
"폰": 766, |
|
"폼": 767, |
|
"표": 768, |
|
"푸": 769, |
|
"품": 770, |
|
"풍": 771, |
|
"퓨": 772, |
|
"프": 773, |
|
"픈": 774, |
|
"플": 775, |
|
"피": 776, |
|
"필": 777, |
|
"핑": 778, |
|
"하": 779, |
|
"학": 780, |
|
"한": 781, |
|
"할": 782, |
|
"함": 783, |
|
"합": 784, |
|
"핫": 785, |
|
"항": 786, |
|
"해": 787, |
|
"핸": 788, |
|
"햇": 789, |
|
"했": 790, |
|
"행": 791, |
|
"향": 792, |
|
"허": 793, |
|
"헐": 794, |
|
"험": 795, |
|
"헤": 796, |
|
"헬": 797, |
|
"혀": 798, |
|
"현": 799, |
|
"혈": 800, |
|
"협": 801, |
|
"형": 802, |
|
"호": 803, |
|
"혹": 804, |
|
"혼": 805, |
|
"홈": 806, |
|
"홍": 807, |
|
"화": 808, |
|
"확": 809, |
|
"환": 810, |
|
"활": 811, |
|
"황": 812, |
|
"회": 813, |
|
"획": 814, |
|
"효": 815, |
|
"후": 816, |
|
"훨": 817, |
|
"휙": 818, |
|
"휴": 819, |
|
"흐": 820, |
|
"흔": 821, |
|
"흘": 822, |
|
"흙": 823, |
|
"흥": 824, |
|
"흩": 825, |
|
"희": 826, |
|
"히": 827, |
|
"힌": 828, |
|
"힐": 829, |
|
"힘": 830 |
|
} |
|
|