wav2vec2-1b-E50 / vocab.json
Gummybear05's picture
Upload tokenizer
e899215 verified
raw
history blame
15.4 kB
{
"(": 1,
")": 2,
":": 3,
"N": 4,
"O": 5,
"P": 6,
"S": 7,
"[PAD]": 1099,
"[UNK]": 1098,
"|": 0,
"가": 8,
"각": 9,
"간": 10,
"갇": 11,
"갈": 12,
"갉": 13,
"감": 14,
"갑": 15,
"값": 16,
"갓": 17,
"갔": 18,
"강": 19,
"갖": 20,
"같": 21,
"갚": 22,
"갛": 23,
"개": 24,
"객": 25,
"갠": 26,
"갱": 27,
"걀": 28,
"걔": 29,
"거": 30,
"걱": 31,
"건": 32,
"걷": 33,
"걸": 34,
"검": 35,
"겁": 36,
"것": 37,
"겄": 38,
"겉": 39,
"게": 40,
"겟": 41,
"겠": 42,
"겨": 43,
"격": 44,
"겪": 45,
"견": 46,
"결": 47,
"겸": 48,
"겹": 49,
"겼": 50,
"경": 51,
"계": 52,
"고": 53,
"곡": 54,
"곤": 55,
"곧": 56,
"골": 57,
"곰": 58,
"곱": 59,
"곳": 60,
"공": 61,
"곶": 62,
"과": 63,
"관": 64,
"광": 65,
"괜": 66,
"괴": 67,
"굉": 68,
"교": 69,
"구": 70,
"국": 71,
"군": 72,
"굳": 73,
"굴": 74,
"굵": 75,
"굶": 76,
"굽": 77,
"궁": 78,
"궈": 79,
"권": 80,
"궐": 81,
"귀": 82,
"규": 83,
"균": 84,
"귤": 85,
"그": 86,
"극": 87,
"근": 88,
"글": 89,
"금": 90,
"급": 91,
"긋": 92,
"긍": 93,
"기": 94,
"긴": 95,
"길": 96,
"김": 97,
"깃": 98,
"깊": 99,
"까": 100,
"깍": 101,
"깎": 102,
"깐": 103,
"깔": 104,
"깜": 105,
"깝": 106,
"깥": 107,
"깨": 108,
"깻": 109,
"깼": 110,
"꺼": 111,
"꺽": 112,
"꺾": 113,
"껀": 114,
"껍": 115,
"께": 116,
"껴": 117,
"꼈": 118,
"꼬": 119,
"꼭": 120,
"꼴": 121,
"꽁": 122,
"꽂": 123,
"꽃": 124,
"꽈": 125,
"꽉": 126,
"꽤": 127,
"꾸": 128,
"꾹": 129,
"꿀": 130,
"꿈": 131,
"꿍": 132,
"꿔": 133,
"뀌": 134,
"뀐": 135,
"뀔": 136,
"끄": 137,
"끊": 138,
"끌": 139,
"끓": 140,
"끔": 141,
"끗": 142,
"끝": 143,
"끼": 144,
"끽": 145,
"낀": 146,
"낄": 147,
"낌": 148,
"나": 149,
"낙": 150,
"낚": 151,
"난": 152,
"날": 153,
"낡": 154,
"남": 155,
"낫": 156,
"났": 157,
"낭": 158,
"낮": 159,
"낳": 160,
"내": 161,
"낸": 162,
"낼": 163,
"냄": 164,
"냅": 165,
"냈": 166,
"냉": 167,
"냐": 168,
"냥": 169,
"너": 170,
"넌": 171,
"널": 172,
"넓": 173,
"넘": 174,
"넙": 175,
"넣": 176,
"네": 177,
"넷": 178,
"녀": 179,
"녁": 180,
"년": 181,
"념": 182,
"녔": 183,
"녕": 184,
"노": 185,
"녹": 186,
"논": 187,
"놀": 188,
"놈": 189,
"농": 190,
"높": 191,
"놓": 192,
"놔": 193,
"놨": 194,
"뇌": 195,
"뇨": 196,
"누": 197,
"눈": 198,
"눌": 199,
"눠": 200,
"눴": 201,
"뉴": 202,
"느": 203,
"는": 204,
"늘": 205,
"늙": 206,
"늠": 207,
"능": 208,
"늦": 209,
"늬": 210,
"니": 211,
"닌": 212,
"닐": 213,
"님": 214,
"닝": 215,
"다": 216,
"닥": 217,
"닦": 218,
"단": 219,
"닫": 220,
"달": 221,
"닭": 222,
"닮": 223,
"담": 224,
"답": 225,
"닷": 226,
"당": 227,
"닿": 228,
"대": 229,
"댁": 230,
"댄": 231,
"댐": 232,
"댑": 233,
"댕": 234,
"더": 235,
"덕": 236,
"던": 237,
"덜": 238,
"덟": 239,
"덤": 240,
"덥": 241,
"덧": 242,
"덩": 243,
"데": 244,
"덴": 245,
"델": 246,
"뎌": 247,
"도": 248,
"독": 249,
"돈": 250,
"돌": 251,
"돔": 252,
"돕": 253,
"동": 254,
"돼": 255,
"됐": 256,
"되": 257,
"된": 258,
"될": 259,
"두": 260,
"둑": 261,
"둔": 262,
"둘": 263,
"둡": 264,
"둬": 265,
"뒀": 266,
"뒤": 267,
"뒷": 268,
"뒹": 269,
"드": 270,
"득": 271,
"든": 272,
"듣": 273,
"들": 274,
"듬": 275,
"듯": 276,
"등": 277,
"디": 278,
"딘": 279,
"딜": 280,
"딩": 281,
"딪": 282,
"따": 283,
"딱": 284,
"딴": 285,
"딸": 286,
"땀": 287,
"땅": 288,
"때": 289,
"땐": 290,
"땜": 291,
"땡": 292,
"떠": 293,
"떡": 294,
"떤": 295,
"떨": 296,
"떻": 297,
"떼": 298,
"또": 299,
"똑": 300,
"뚝": 301,
"뚱": 302,
"뛰": 303,
"뜨": 304,
"뜩": 305,
"뜬": 306,
"뜯": 307,
"뜰": 308,
"뜹": 309,
"뜻": 310,
"띄": 311,
"띠": 312,
"띵": 313,
"라": 314,
"락": 315,
"란": 316,
"랄": 317,
"람": 318,
"랏": 319,
"랐": 320,
"랑": 321,
"랗": 322,
"래": 323,
"랜": 324,
"램": 325,
"랫": 326,
"랬": 327,
"랭": 328,
"략": 329,
"량": 330,
"러": 331,
"런": 332,
"럴": 333,
"럼": 334,
"럽": 335,
"럿": 336,
"렀": 337,
"렁": 338,
"렇": 339,
"레": 340,
"렉": 341,
"렌": 342,
"려": 343,
"력": 344,
"련": 345,
"렬": 346,
"렴": 347,
"렵": 348,
"렸": 349,
"령": 350,
"례": 351,
"로": 352,
"록": 353,
"론": 354,
"롤": 355,
"롭": 356,
"롯": 357,
"롱": 358,
"뢰": 359,
"료": 360,
"룡": 361,
"루": 362,
"룩": 363,
"룬": 364,
"룸": 365,
"룻": 366,
"뤄": 367,
"류": 368,
"륙": 369,
"륜": 370,
"률": 371,
"륨": 372,
"륭": 373,
"르": 374,
"른": 375,
"를": 376,
"름": 377,
"릇": 378,
"릉": 379,
"릎": 380,
"릏": 381,
"리": 382,
"린": 383,
"릴": 384,
"림": 385,
"립": 386,
"릿": 387,
"링": 388,
"마": 389,
"막": 390,
"만": 391,
"많": 392,
"말": 393,
"맑": 394,
"맘": 395,
"맙": 396,
"맛": 397,
"망": 398,
"맞": 399,
"맡": 400,
"맣": 401,
"매": 402,
"맥": 403,
"맨": 404,
"맵": 405,
"맹": 406,
"맺": 407,
"머": 408,
"먹": 409,
"먼": 410,
"멀": 411,
"멈": 412,
"멋": 413,
"멍": 414,
"메": 415,
"멘": 416,
"멧": 417,
"며": 418,
"면": 419,
"멸": 420,
"명": 421,
"몇": 422,
"모": 423,
"목": 424,
"몬": 425,
"몰": 426,
"몸": 427,
"못": 428,
"몽": 429,
"묘": 430,
"무": 431,
"묵": 432,
"문": 433,
"묻": 434,
"물": 435,
"뭇": 436,
"뭉": 437,
"뭐": 438,
"뭔": 439,
"뭘": 440,
"뭡": 441,
"뮤": 442,
"믄": 443,
"미": 444,
"믹": 445,
"민": 446,
"믿": 447,
"밀": 448,
"밉": 449,
"밌": 450,
"밍": 451,
"밑": 452,
"바": 453,
"박": 454,
"밖": 455,
"반": 456,
"받": 457,
"발": 458,
"밝": 459,
"밟": 460,
"밤": 461,
"밥": 462,
"방": 463,
"밭": 464,
"배": 465,
"백": 466,
"뱃": 467,
"뱅": 468,
"버": 469,
"벅": 470,
"번": 471,
"벌": 472,
"범": 473,
"법": 474,
"벗": 475,
"벚": 476,
"베": 477,
"벤": 478,
"벨": 479,
"벼": 480,
"벽": 481,
"변": 482,
"별": 483,
"볍": 484,
"볏": 485,
"병": 486,
"보": 487,
"복": 488,
"볶": 489,
"본": 490,
"볼": 491,
"봄": 492,
"봅": 493,
"봇": 494,
"봉": 495,
"봐": 496,
"봤": 497,
"부": 498,
"북": 499,
"분": 500,
"불": 501,
"붉": 502,
"붓": 503,
"붕": 504,
"붙": 505,
"뷔": 506,
"브": 507,
"블": 508,
"비": 509,
"빅": 510,
"빈": 511,
"빌": 512,
"빙": 513,
"빚": 514,
"빛": 515,
"빠": 516,
"빡": 517,
"빨": 518,
"빵": 519,
"빼": 520,
"빽": 521,
"뺀": 522,
"뺄": 523,
"뺏": 524,
"뺐": 525,
"뻐": 526,
"뻔": 527,
"뻠": 528,
"뻣": 529,
"뻤": 530,
"뼈": 531,
"뽀": 532,
"뽈": 533,
"뽑": 534,
"뽕": 535,
"뿌": 536,
"뿍": 537,
"뿐": 538,
"쁘": 539,
"쁜": 540,
"쁠": 541,
"삐": 542,
"사": 543,
"삭": 544,
"산": 545,
"살": 546,
"삶": 547,
"삼": 548,
"샀": 549,
"상": 550,
"새": 551,
"색": 552,
"샘": 553,
"생": 554,
"샵": 555,
"서": 556,
"석": 557,
"섞": 558,
"선": 559,
"설": 560,
"섬": 561,
"섭": 562,
"섯": 563,
"성": 564,
"세": 565,
"센": 566,
"셋": 567,
"셔": 568,
"션": 569,
"셜": 570,
"셨": 571,
"셰": 572,
"소": 573,
"속": 574,
"손": 575,
"솔": 576,
"솜": 577,
"솟": 578,
"송": 579,
"솥": 580,
"쇄": 581,
"쇠": 582,
"쇼": 583,
"숍": 584,
"수": 585,
"숙": 586,
"순": 587,
"숟": 588,
"술": 589,
"숨": 590,
"숭": 591,
"숯": 592,
"숲": 593,
"쉐": 594,
"쉬": 595,
"쉴": 596,
"쉼": 597,
"쉽": 598,
"슐": 599,
"슘": 600,
"스": 601,
"슨": 602,
"슬": 603,
"슭": 604,
"슴": 605,
"습": 606,
"슷": 607,
"승": 608,
"시": 609,
"식": 610,
"신": 611,
"실": 612,
"싫": 613,
"심": 614,
"십": 615,
"싱": 616,
"싶": 617,
"싸": 618,
"싹": 619,
"싼": 620,
"쌈": 621,
"쌌": 622,
"쌓": 623,
"쌤": 624,
"써": 625,
"썩": 626,
"썬": 627,
"썰": 628,
"썼": 629,
"쎄": 630,
"쎗": 631,
"쏘": 632,
"쏟": 633,
"쏠": 634,
"쐬": 635,
"쑤": 636,
"쑥": 637,
"쓰": 638,
"쓴": 639,
"쓸": 640,
"씀": 641,
"씌": 642,
"씨": 643,
"씩": 644,
"씬": 645,
"씹": 646,
"씻": 647,
"아": 648,
"악": 649,
"안": 650,
"앉": 651,
"않": 652,
"알": 653,
"앓": 654,
"암": 655,
"압": 656,
"앗": 657,
"았": 658,
"앞": 659,
"애": 660,
"액": 661,
"앤": 662,
"앨": 663,
"야": 664,
"약": 665,
"얀": 666,
"얇": 667,
"양": 668,
"얗": 669,
"얘": 670,
"어": 671,
"억": 672,
"언": 673,
"얹": 674,
"얻": 675,
"얼": 676,
"얽": 677,
"엄": 678,
"업": 679,
"없": 680,
"엇": 681,
"었": 682,
"엉": 683,
"엊": 684,
"엎": 685,
"에": 686,
"엑": 687,
"엔": 688,
"엘": 689,
"엠": 690,
"여": 691,
"역": 692,
"엮": 693,
"연": 694,
"열": 695,
"염": 696,
"엽": 697,
"엿": 698,
"였": 699,
"영": 700,
"옆": 701,
"예": 702,
"옛": 703,
"오": 704,
"옥": 705,
"온": 706,
"올": 707,
"옮": 708,
"옷": 709,
"와": 710,
"완": 711,
"왈": 712,
"왓": 713,
"왔": 714,
"왕": 715,
"왜": 716,
"왠": 717,
"외": 718,
"왼": 719,
"요": 720,
"욕": 721,
"욜": 722,
"용": 723,
"우": 724,
"욱": 725,
"운": 726,
"울": 727,
"움": 728,
"웃": 729,
"웅": 730,
"워": 731,
"원": 732,
"월": 733,
"웠": 734,
"웨": 735,
"웬": 736,
"위": 737,
"윙": 738,
"유": 739,
"육": 740,
"윤": 741,
"율": 742,
"으": 743,
"은": 744,
"을": 745,
"음": 746,
"응": 747,
"의": 748,
"이": 749,
"익": 750,
"인": 751,
"일": 752,
"읽": 753,
"잃": 754,
"임": 755,
"입": 756,
"잇": 757,
"있": 758,
"잉": 759,
"잊": 760,
"잎": 761,
"자": 762,
"작": 763,
"잔": 764,
"잖": 765,
"잘": 766,
"잠": 767,
"잡": 768,
"잣": 769,
"장": 770,
"재": 771,
"쟁": 772,
"저": 773,
"적": 774,
"전": 775,
"절": 776,
"젊": 777,
"점": 778,
"접": 779,
"젓": 780,
"정": 781,
"젖": 782,
"제": 783,
"젠": 784,
"져": 785,
"졌": 786,
"조": 787,
"족": 788,
"존": 789,
"졸": 790,
"좀": 791,
"좁": 792,
"종": 793,
"좋": 794,
"좌": 795,
"죠": 796,
"주": 797,
"죽": 798,
"준": 799,
"줄": 800,
"줌": 801,
"중": 802,
"줘": 803,
"줬": 804,
"쥐": 805,
"즈": 806,
"즉": 807,
"즌": 808,
"즐": 809,
"즘": 810,
"즙": 811,
"증": 812,
"지": 813,
"직": 814,
"진": 815,
"질": 816,
"집": 817,
"짓": 818,
"징": 819,
"짙": 820,
"짚": 821,
"짜": 822,
"짝": 823,
"짠": 824,
"짧": 825,
"짰": 826,
"짱": 827,
"째": 828,
"쨋": 829,
"쨌": 830,
"쩍": 831,
"쩔": 832,
"쩜": 833,
"쪄": 834,
"쪘": 835,
"쪼": 836,
"쪽": 837,
"쫄": 838,
"쫌": 839,
"쫙": 840,
"쬐": 841,
"쭉": 842,
"쭤": 843,
"쯤": 844,
"찌": 845,
"찍": 846,
"찐": 847,
"찔": 848,
"찜": 849,
"찝": 850,
"찡": 851,
"찢": 852,
"차": 853,
"착": 854,
"찬": 855,
"찮": 856,
"찰": 857,
"참": 858,
"찻": 859,
"찼": 860,
"창": 861,
"찾": 862,
"채": 863,
"책": 864,
"챙": 865,
"처": 866,
"척": 867,
"천": 868,
"철": 869,
"첨": 870,
"첩": 871,
"첫": 872,
"청": 873,
"체": 874,
"쳐": 875,
"쳤": 876,
"초": 877,
"촌": 878,
"총": 879,
"촬": 880,
"최": 881,
"추": 882,
"축": 883,
"춘": 884,
"출": 885,
"춤": 886,
"춥": 887,
"춧": 888,
"충": 889,
"춰": 890,
"췄": 891,
"췌": 892,
"취": 893,
"츠": 894,
"측": 895,
"츰": 896,
"층": 897,
"치": 898,
"칙": 899,
"친": 900,
"칠": 901,
"칡": 902,
"침": 903,
"칫": 904,
"칭": 905,
"카": 906,
"칵": 907,
"칸": 908,
"칼": 909,
"캉": 910,
"캐": 911,
"캠": 912,
"캡": 913,
"캤": 914,
"커": 915,
"컨": 916,
"컬": 917,
"컴": 918,
"컷": 919,
"컸": 920,
"케": 921,
"켓": 922,
"켜": 923,
"켰": 924,
"코": 925,
"콕": 926,
"콘": 927,
"콜": 928,
"콤": 929,
"콩": 930,
"쾌": 931,
"쿠": 932,
"쿼": 933,
"퀴": 934,
"크": 935,
"큰": 936,
"클": 937,
"큼": 938,
"키": 939,
"킨": 940,
"킬": 941,
"킹": 942,
"타": 943,
"탁": 944,
"탄": 945,
"탈": 946,
"탐": 947,
"탑": 948,
"탔": 949,
"탕": 950,
"태": 951,
"택": 952,
"탬": 953,
"터": 954,
"턴": 955,
"털": 956,
"텁": 957,
"텃": 958,
"텅": 959,
"테": 960,
"텍": 961,
"텐": 962,
"텔": 963,
"템": 964,
"토": 965,
"톡": 966,
"톤": 967,
"톱": 968,
"통": 969,
"퇴": 970,
"투": 971,
"툭": 972,
"퉁": 973,
"튀": 974,
"튈": 975,
"튜": 976,
"트": 977,
"특": 978,
"튼": 979,
"튿": 980,
"틀": 981,
"티": 982,
"틱": 983,
"틴": 984,
"팀": 985,
"팁": 986,
"팅": 987,
"파": 988,
"팍": 989,
"판": 990,
"팔": 991,
"팠": 992,
"팡": 993,
"팥": 994,
"패": 995,
"팩": 996,
"팬": 997,
"팰": 998,
"퍼": 999,
"퍽": 1000,
"펌": 1001,
"페": 1002,
"펙": 1003,
"펜": 1004,
"편": 1005,
"폈": 1006,
"평": 1007,
"폐": 1008,
"포": 1009,
"폭": 1010,
"폰": 1011,
"폴": 1012,
"폼": 1013,
"표": 1014,
"푸": 1015,
"푹": 1016,
"푼": 1017,
"풀": 1018,
"품": 1019,
"풍": 1020,
"퓨": 1021,
"프": 1022,
"픈": 1023,
"플": 1024,
"피": 1025,
"픽": 1026,
"필": 1027,
"핍": 1028,
"핏": 1029,
"핑": 1030,
"하": 1031,
"학": 1032,
"한": 1033,
"할": 1034,
"함": 1035,
"합": 1036,
"핫": 1037,
"항": 1038,
"해": 1039,
"핸": 1040,
"햄": 1041,
"햇": 1042,
"했": 1043,
"행": 1044,
"향": 1045,
"허": 1046,
"헌": 1047,
"헐": 1048,
"험": 1049,
"헤": 1050,
"헬": 1051,
"혀": 1052,
"현": 1053,
"혈": 1054,
"협": 1055,
"혔": 1056,
"형": 1057,
"혜": 1058,
"호": 1059,
"혹": 1060,
"혼": 1061,
"홀": 1062,
"홈": 1063,
"홉": 1064,
"홍": 1065,
"화": 1066,
"확": 1067,
"환": 1068,
"활": 1069,
"황": 1070,
"회": 1071,
"획": 1072,
"횟": 1073,
"횡": 1074,
"효": 1075,
"후": 1076,
"훅": 1077,
"훈": 1078,
"훌": 1079,
"훔": 1080,
"훨": 1081,
"휙": 1082,
"휴": 1083,
"흉": 1084,
"흐": 1085,
"흑": 1086,
"흔": 1087,
"흘": 1088,
"흙": 1089,
"흡": 1090,
"흥": 1091,
"흩": 1092,
"희": 1093,
"히": 1094,
"힌": 1095,
"힐": 1096,
"힘": 1097
}