wav2vec2-E30 / vocab.json
Gummybear05's picture
Upload tokenizer
5202dac verified
raw
history blame
14.2 kB
{
"(": 1,
")": 2,
"[PAD]": 1018,
"[UNK]": 1017,
"n": 3,
"o": 4,
"p": 5,
"s": 6,
"|": 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,
"갛": 21,
"개": 22,
"객": 23,
"갠": 24,
"갱": 25,
"걔": 26,
"거": 27,
"걱": 28,
"건": 29,
"걷": 30,
"걸": 31,
"검": 32,
"겁": 33,
"것": 34,
"겄": 35,
"겉": 36,
"게": 37,
"겟": 38,
"겠": 39,
"겨": 40,
"격": 41,
"겪": 42,
"견": 43,
"결": 44,
"겸": 45,
"겹": 46,
"겼": 47,
"경": 48,
"계": 49,
"고": 50,
"곤": 51,
"곧": 52,
"골": 53,
"곰": 54,
"곱": 55,
"곳": 56,
"공": 57,
"곶": 58,
"과": 59,
"관": 60,
"광": 61,
"괜": 62,
"괴": 63,
"굉": 64,
"교": 65,
"구": 66,
"국": 67,
"군": 68,
"굳": 69,
"굴": 70,
"굵": 71,
"굶": 72,
"굽": 73,
"궁": 74,
"궈": 75,
"권": 76,
"궐": 77,
"귀": 78,
"규": 79,
"균": 80,
"그": 81,
"극": 82,
"근": 83,
"글": 84,
"금": 85,
"급": 86,
"긍": 87,
"기": 88,
"긴": 89,
"길": 90,
"김": 91,
"깃": 92,
"깊": 93,
"까": 94,
"깍": 95,
"깎": 96,
"깐": 97,
"깔": 98,
"깜": 99,
"깝": 100,
"깥": 101,
"깨": 102,
"깻": 103,
"깼": 104,
"꺼": 105,
"꺽": 106,
"꺾": 107,
"껀": 108,
"껍": 109,
"께": 110,
"껴": 111,
"꼈": 112,
"꼬": 113,
"꼭": 114,
"꽁": 115,
"꽃": 116,
"꽤": 117,
"꾸": 118,
"꿀": 119,
"꿈": 120,
"꿍": 121,
"꿔": 122,
"뀌": 123,
"뀐": 124,
"뀔": 125,
"끄": 126,
"끊": 127,
"끌": 128,
"끓": 129,
"끔": 130,
"끗": 131,
"끝": 132,
"끼": 133,
"끽": 134,
"낀": 135,
"낄": 136,
"낌": 137,
"나": 138,
"낙": 139,
"낚": 140,
"난": 141,
"날": 142,
"낡": 143,
"남": 144,
"낫": 145,
"났": 146,
"낭": 147,
"낮": 148,
"내": 149,
"낸": 150,
"낼": 151,
"냄": 152,
"냅": 153,
"냈": 154,
"냉": 155,
"냐": 156,
"냥": 157,
"너": 158,
"넓": 159,
"넘": 160,
"넙": 161,
"넣": 162,
"네": 163,
"넷": 164,
"녀": 165,
"녁": 166,
"년": 167,
"념": 168,
"녔": 169,
"노": 170,
"녹": 171,
"논": 172,
"놀": 173,
"놈": 174,
"농": 175,
"높": 176,
"놓": 177,
"놔": 178,
"놨": 179,
"뇌": 180,
"뇨": 181,
"누": 182,
"눈": 183,
"눌": 184,
"눠": 185,
"뉴": 186,
"느": 187,
"는": 188,
"늘": 189,
"늙": 190,
"능": 191,
"늦": 192,
"늬": 193,
"니": 194,
"닌": 195,
"닐": 196,
"님": 197,
"닝": 198,
"다": 199,
"닥": 200,
"단": 201,
"닫": 202,
"달": 203,
"닭": 204,
"닮": 205,
"담": 206,
"답": 207,
"닷": 208,
"당": 209,
"닿": 210,
"대": 211,
"댁": 212,
"댄": 213,
"댐": 214,
"댑": 215,
"댕": 216,
"더": 217,
"덕": 218,
"던": 219,
"덜": 220,
"덟": 221,
"덤": 222,
"덥": 223,
"덩": 224,
"데": 225,
"덴": 226,
"델": 227,
"뎌": 228,
"도": 229,
"독": 230,
"돈": 231,
"돌": 232,
"돕": 233,
"동": 234,
"돼": 235,
"됐": 236,
"되": 237,
"된": 238,
"될": 239,
"두": 240,
"둑": 241,
"둔": 242,
"둘": 243,
"둡": 244,
"둬": 245,
"뒀": 246,
"뒤": 247,
"뒷": 248,
"뒹": 249,
"드": 250,
"득": 251,
"든": 252,
"듣": 253,
"들": 254,
"듬": 255,
"듯": 256,
"등": 257,
"디": 258,
"딘": 259,
"딜": 260,
"딩": 261,
"딪": 262,
"따": 263,
"딱": 264,
"딴": 265,
"딸": 266,
"땀": 267,
"땅": 268,
"때": 269,
"땐": 270,
"땜": 271,
"땡": 272,
"떠": 273,
"떡": 274,
"떤": 275,
"떨": 276,
"떻": 277,
"또": 278,
"똑": 279,
"뚱": 280,
"뛰": 281,
"뜨": 282,
"뜩": 283,
"뜬": 284,
"뜯": 285,
"뜰": 286,
"뜹": 287,
"뜻": 288,
"띄": 289,
"띠": 290,
"띵": 291,
"라": 292,
"락": 293,
"란": 294,
"랄": 295,
"람": 296,
"랏": 297,
"랐": 298,
"랑": 299,
"랗": 300,
"래": 301,
"랜": 302,
"램": 303,
"랫": 304,
"랬": 305,
"랭": 306,
"략": 307,
"량": 308,
"러": 309,
"런": 310,
"럴": 311,
"럼": 312,
"럽": 313,
"렀": 314,
"렁": 315,
"렇": 316,
"레": 317,
"렉": 318,
"렌": 319,
"려": 320,
"력": 321,
"련": 322,
"렬": 323,
"렴": 324,
"렵": 325,
"렸": 326,
"령": 327,
"례": 328,
"로": 329,
"록": 330,
"론": 331,
"롤": 332,
"롭": 333,
"롯": 334,
"롱": 335,
"뢰": 336,
"료": 337,
"루": 338,
"룩": 339,
"룬": 340,
"룸": 341,
"룻": 342,
"류": 343,
"륙": 344,
"륜": 345,
"률": 346,
"륨": 347,
"륭": 348,
"르": 349,
"른": 350,
"를": 351,
"름": 352,
"릇": 353,
"릉": 354,
"릎": 355,
"리": 356,
"린": 357,
"릴": 358,
"림": 359,
"립": 360,
"릿": 361,
"링": 362,
"마": 363,
"막": 364,
"만": 365,
"많": 366,
"말": 367,
"맑": 368,
"맘": 369,
"맙": 370,
"맛": 371,
"망": 372,
"맞": 373,
"맣": 374,
"매": 375,
"맥": 376,
"맨": 377,
"맵": 378,
"맹": 379,
"맺": 380,
"머": 381,
"먹": 382,
"먼": 383,
"멀": 384,
"멈": 385,
"멋": 386,
"멍": 387,
"메": 388,
"멘": 389,
"멧": 390,
"며": 391,
"면": 392,
"멸": 393,
"명": 394,
"몇": 395,
"모": 396,
"목": 397,
"몬": 398,
"몰": 399,
"몸": 400,
"못": 401,
"몽": 402,
"묘": 403,
"무": 404,
"묵": 405,
"문": 406,
"물": 407,
"뭇": 408,
"뭐": 409,
"뭔": 410,
"뭘": 411,
"뭡": 412,
"뮤": 413,
"믄": 414,
"미": 415,
"믹": 416,
"민": 417,
"믿": 418,
"밀": 419,
"밉": 420,
"밌": 421,
"밍": 422,
"밑": 423,
"바": 424,
"박": 425,
"밖": 426,
"반": 427,
"받": 428,
"발": 429,
"밝": 430,
"밤": 431,
"밥": 432,
"방": 433,
"밭": 434,
"배": 435,
"백": 436,
"뱃": 437,
"버": 438,
"벅": 439,
"번": 440,
"벌": 441,
"범": 442,
"법": 443,
"벚": 444,
"베": 445,
"벤": 446,
"벨": 447,
"벼": 448,
"벽": 449,
"변": 450,
"별": 451,
"볍": 452,
"볏": 453,
"병": 454,
"보": 455,
"복": 456,
"볶": 457,
"본": 458,
"볼": 459,
"봄": 460,
"봇": 461,
"봉": 462,
"봐": 463,
"봤": 464,
"부": 465,
"북": 466,
"분": 467,
"불": 468,
"붉": 469,
"붓": 470,
"붕": 471,
"붙": 472,
"뷔": 473,
"브": 474,
"블": 475,
"비": 476,
"빅": 477,
"빈": 478,
"빌": 479,
"빙": 480,
"빛": 481,
"빠": 482,
"빡": 483,
"빨": 484,
"빵": 485,
"빼": 486,
"빽": 487,
"뺀": 488,
"뺄": 489,
"뺐": 490,
"뻐": 491,
"뻔": 492,
"뻣": 493,
"뻤": 494,
"뼈": 495,
"뽀": 496,
"뽈": 497,
"뽑": 498,
"뿌": 499,
"뿍": 500,
"뿐": 501,
"쁘": 502,
"쁜": 503,
"삐": 504,
"사": 505,
"삭": 506,
"산": 507,
"살": 508,
"삶": 509,
"삼": 510,
"샀": 511,
"상": 512,
"새": 513,
"색": 514,
"샘": 515,
"생": 516,
"샵": 517,
"서": 518,
"석": 519,
"섞": 520,
"선": 521,
"설": 522,
"섬": 523,
"섭": 524,
"섯": 525,
"성": 526,
"세": 527,
"센": 528,
"셋": 529,
"셔": 530,
"션": 531,
"셜": 532,
"셨": 533,
"셰": 534,
"소": 535,
"속": 536,
"손": 537,
"솔": 538,
"솜": 539,
"솟": 540,
"송": 541,
"솥": 542,
"쇄": 543,
"쇠": 544,
"쇼": 545,
"숍": 546,
"수": 547,
"숙": 548,
"순": 549,
"숟": 550,
"술": 551,
"숨": 552,
"숭": 553,
"숲": 554,
"쉐": 555,
"쉬": 556,
"쉴": 557,
"쉽": 558,
"슐": 559,
"슘": 560,
"스": 561,
"슨": 562,
"슬": 563,
"슭": 564,
"슴": 565,
"습": 566,
"슷": 567,
"승": 568,
"시": 569,
"식": 570,
"신": 571,
"실": 572,
"싫": 573,
"심": 574,
"십": 575,
"싱": 576,
"싶": 577,
"싸": 578,
"싹": 579,
"싼": 580,
"쌈": 581,
"쌌": 582,
"쌤": 583,
"써": 584,
"썩": 585,
"썬": 586,
"썰": 587,
"썼": 588,
"쎄": 589,
"쏟": 590,
"쑤": 591,
"쑥": 592,
"쓰": 593,
"쓴": 594,
"쓸": 595,
"씀": 596,
"씌": 597,
"씨": 598,
"씩": 599,
"씬": 600,
"씹": 601,
"씻": 602,
"아": 603,
"악": 604,
"안": 605,
"앉": 606,
"않": 607,
"알": 608,
"앓": 609,
"암": 610,
"압": 611,
"앗": 612,
"았": 613,
"앞": 614,
"애": 615,
"액": 616,
"앤": 617,
"앨": 618,
"야": 619,
"약": 620,
"얇": 621,
"양": 622,
"얗": 623,
"얘": 624,
"어": 625,
"억": 626,
"언": 627,
"얻": 628,
"얼": 629,
"엄": 630,
"업": 631,
"없": 632,
"엇": 633,
"었": 634,
"엉": 635,
"엊": 636,
"엎": 637,
"에": 638,
"엑": 639,
"엔": 640,
"엘": 641,
"여": 642,
"역": 643,
"엮": 644,
"연": 645,
"열": 646,
"염": 647,
"엽": 648,
"였": 649,
"영": 650,
"옆": 651,
"예": 652,
"옛": 653,
"오": 654,
"옥": 655,
"온": 656,
"올": 657,
"옷": 658,
"와": 659,
"완": 660,
"왓": 661,
"왔": 662,
"왕": 663,
"왜": 664,
"외": 665,
"요": 666,
"욕": 667,
"욜": 668,
"용": 669,
"우": 670,
"욱": 671,
"운": 672,
"울": 673,
"움": 674,
"웃": 675,
"웅": 676,
"워": 677,
"원": 678,
"월": 679,
"웠": 680,
"웨": 681,
"웬": 682,
"위": 683,
"유": 684,
"육": 685,
"윤": 686,
"율": 687,
"으": 688,
"은": 689,
"을": 690,
"음": 691,
"응": 692,
"의": 693,
"이": 694,
"익": 695,
"인": 696,
"일": 697,
"읽": 698,
"임": 699,
"입": 700,
"잇": 701,
"있": 702,
"잊": 703,
"잎": 704,
"자": 705,
"작": 706,
"잔": 707,
"잖": 708,
"잘": 709,
"잠": 710,
"잡": 711,
"잣": 712,
"장": 713,
"재": 714,
"쟁": 715,
"저": 716,
"적": 717,
"전": 718,
"절": 719,
"젊": 720,
"점": 721,
"접": 722,
"젓": 723,
"정": 724,
"젖": 725,
"제": 726,
"젠": 727,
"져": 728,
"졌": 729,
"조": 730,
"족": 731,
"존": 732,
"졸": 733,
"좀": 734,
"좁": 735,
"종": 736,
"좋": 737,
"좌": 738,
"죠": 739,
"주": 740,
"죽": 741,
"준": 742,
"줄": 743,
"줌": 744,
"중": 745,
"줘": 746,
"줬": 747,
"쥐": 748,
"즈": 749,
"즉": 750,
"즌": 751,
"즐": 752,
"즘": 753,
"즙": 754,
"증": 755,
"지": 756,
"직": 757,
"진": 758,
"질": 759,
"집": 760,
"짓": 761,
"징": 762,
"짜": 763,
"짝": 764,
"짠": 765,
"짧": 766,
"짰": 767,
"짱": 768,
"째": 769,
"쨌": 770,
"쩍": 771,
"쩔": 772,
"쩜": 773,
"쪄": 774,
"쪘": 775,
"쪼": 776,
"쪽": 777,
"쫄": 778,
"쫌": 779,
"쫙": 780,
"쬐": 781,
"쭉": 782,
"쯤": 783,
"찌": 784,
"찍": 785,
"찐": 786,
"찔": 787,
"찜": 788,
"찝": 789,
"찢": 790,
"차": 791,
"착": 792,
"찬": 793,
"찮": 794,
"찰": 795,
"참": 796,
"찻": 797,
"창": 798,
"찾": 799,
"채": 800,
"책": 801,
"챙": 802,
"처": 803,
"척": 804,
"천": 805,
"철": 806,
"첨": 807,
"첩": 808,
"첫": 809,
"청": 810,
"체": 811,
"쳐": 812,
"쳤": 813,
"초": 814,
"총": 815,
"촬": 816,
"최": 817,
"추": 818,
"축": 819,
"춘": 820,
"출": 821,
"춤": 822,
"춥": 823,
"춧": 824,
"충": 825,
"춰": 826,
"췄": 827,
"췌": 828,
"취": 829,
"측": 830,
"츰": 831,
"층": 832,
"치": 833,
"칙": 834,
"친": 835,
"칠": 836,
"칡": 837,
"침": 838,
"칫": 839,
"칭": 840,
"카": 841,
"칵": 842,
"칸": 843,
"칼": 844,
"캉": 845,
"캐": 846,
"캠": 847,
"캡": 848,
"캤": 849,
"커": 850,
"컨": 851,
"컬": 852,
"컴": 853,
"컷": 854,
"컸": 855,
"케": 856,
"켓": 857,
"켜": 858,
"켰": 859,
"코": 860,
"콕": 861,
"콘": 862,
"콜": 863,
"콩": 864,
"쾌": 865,
"쿠": 866,
"쿼": 867,
"퀴": 868,
"크": 869,
"큰": 870,
"클": 871,
"큼": 872,
"키": 873,
"킨": 874,
"킬": 875,
"킹": 876,
"타": 877,
"탁": 878,
"탄": 879,
"탈": 880,
"탐": 881,
"탑": 882,
"탔": 883,
"탕": 884,
"태": 885,
"택": 886,
"탬": 887,
"터": 888,
"턴": 889,
"털": 890,
"텁": 891,
"텃": 892,
"텅": 893,
"테": 894,
"텍": 895,
"텐": 896,
"텔": 897,
"템": 898,
"토": 899,
"톡": 900,
"톤": 901,
"통": 902,
"퇴": 903,
"투": 904,
"툭": 905,
"퉁": 906,
"튀": 907,
"튈": 908,
"튜": 909,
"트": 910,
"특": 911,
"튼": 912,
"튿": 913,
"틀": 914,
"티": 915,
"틱": 916,
"틴": 917,
"팀": 918,
"팅": 919,
"파": 920,
"팍": 921,
"판": 922,
"팔": 923,
"팠": 924,
"팥": 925,
"패": 926,
"팰": 927,
"퍼": 928,
"펌": 929,
"페": 930,
"펜": 931,
"편": 932,
"평": 933,
"폐": 934,
"포": 935,
"폭": 936,
"폰": 937,
"폼": 938,
"표": 939,
"푸": 940,
"푹": 941,
"푼": 942,
"풀": 943,
"품": 944,
"풍": 945,
"퓨": 946,
"프": 947,
"픈": 948,
"플": 949,
"피": 950,
"필": 951,
"핍": 952,
"핏": 953,
"핑": 954,
"하": 955,
"학": 956,
"한": 957,
"할": 958,
"함": 959,
"합": 960,
"핫": 961,
"항": 962,
"해": 963,
"핸": 964,
"햄": 965,
"햇": 966,
"했": 967,
"행": 968,
"향": 969,
"허": 970,
"헐": 971,
"험": 972,
"헤": 973,
"헬": 974,
"혀": 975,
"현": 976,
"혈": 977,
"협": 978,
"혔": 979,
"형": 980,
"혜": 981,
"호": 982,
"혹": 983,
"혼": 984,
"홈": 985,
"홉": 986,
"홍": 987,
"화": 988,
"확": 989,
"환": 990,
"활": 991,
"황": 992,
"회": 993,
"획": 994,
"횟": 995,
"횡": 996,
"효": 997,
"후": 998,
"훈": 999,
"훌": 1000,
"훨": 1001,
"휙": 1002,
"휴": 1003,
"흉": 1004,
"흐": 1005,
"흔": 1006,
"흘": 1007,
"흙": 1008,
"흡": 1009,
"흥": 1010,
"흩": 1011,
"희": 1012,
"히": 1013,
"힌": 1014,
"힐": 1015,
"힘": 1016
}