Doogie commited on
Commit
6a4f75e
โ€ข
1 Parent(s): ab08c60

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer_config.json +1 -0
  3. vocab.json +1 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"๋Š": 0, "ํ”„": 1, "๋น ": 2, "์™€": 3, "์ค„": 4, "๋“ฃ": 5, "๋นš": 6, "๋žจ": 7, "๊ดœ": 8, "๋‹ต": 9, "ํ• ": 10, "์ˆ‘": 11, "๋ถ": 12, "๋ณ‘": 13, "๋‹จ": 14, "๋ด‡": 15, "๋‹ฟ": 16, "ํ•ด": 17, "๊ฐ•": 18, "์ชผ": 19, "ํƒˆ": 20, "๋ทฐ": 21, "๋ชป": 22, "๋‚Œ": 23, "๋…": 24, "๊ทน": 25, "ํฌ": 26, "์ธ": 27, "์ˆ ": 28, "๋ฝ‘": 29, "์ค‘": 30, "์Ÿ": 31, "์งค": 32, "๊ฒช": 33, "๋งจ": 34, "์ฐฎ": 35, "์ค€": 36, "๋“ฑ": 37, "๋ฃฌ": 38, "์‚ด": 39, "๋ง": 40, "ํ‚ด": 41, "ํ…ฌ": 42, "ํŒฌ": 43, "๋‰ด": 44, "๋–ป": 45, "์ง": 46, "ํƒ„": 47, "q": 48, "ํƒ•": 49, "์งˆ": 50, "์ž‡": 51, "์—ด": 52, "์†”": 53, "์œก": 54, "ํŒ…": 55, "์ผ“": 56, "๊ณค": 57, "๋Œ€": 58, "๋น™": 59, "๋‚ฉ": 60, "๊ต": 61, "์ต": 62, "ํ": 63, "ํ—จ": 64, "์‹ญ": 65, "์ฒญ": 66, "ํ€„": 67, "์Šจ": 68, "ํ‘œ": 69, "์‹ฑ": 70, "๊ด„": 71, "๋ฆฐ": 72, "์“ธ": 73, "์ปธ": 74, "ํƒœ": 75, "๋ฌป": 76, "ํ„ฐ": 77, "๋น—": 78, "๋ก ": 79, "์•„": 80, "๋นˆ": 81, "์—˜": 82, "๋ธ”": 83, "ํ”ผ": 84, "๋งˆ": 85, "๋…": 86, "7": 87, "์ด": 88, "๋ถˆ": 89, "y": 90, "c": 91, "ํžŒ": 92, "ํ•™": 93, "๋•€": 94, "์ฝ•": 95, "ํ„ฑ": 96, "์žฅ": 97, "์ œ": 98, "์  ": 99, "๊ณจ": 100, "p": 101, "๋„ค": 102, "์žƒ": 103, "๊ฑด": 104, "ํ—ˆ": 105, "์˜Œ": 106, "๊ธ": 107, "์˜€": 108, "1": 109, "๋• ": 110, "์†Œ": 111, "๋ช…": 112, "ํšŒ": 113, "ํŠธ": 114, "๋”ช": 115, "๋ฆฝ": 116, "๋…•": 117, "ใ…": 118, "ํ‹€": 119, "๋‚˜": 120, "๋ณธ": 121, "์—": 122, "๋Ÿผ": 123, "๋”ด": 124, "b": 125, "๋“": 126, "์šด": 127, "๊ฒจ": 128, "๋ จ": 129, "๋ฉ˜": 130, "๋’ค": 131, "๋ฒ—": 132, "์ ค": 133, "๋Šฌ": 134, "ํ†ค": 135, "๊ณฐ": 136, "์”ฌ": 137, "๋†": 138, "์ฝค": 139, "์…‹": 140, "๋งฅ": 141, "์›จ": 142, "๋“ ": 143, "๋ฆ…": 144, "์ฒด": 145, "์จŒ": 146, "์˜น": 147, "์ฟผ": 148, "์˜จ": 149, "๋ฉˆ": 150, "๊ฝค": 151, "์˜": 152, "๊พธ": 153, "์ง•": 154, "๊ฒ ": 155, "ํ™ฉ": 156, "์žค": 157, "ํฅ": 158, "์œ ": 159, "๊ท ": 160, "๊ธด": 161, "๋ญ": 162, "์ ": 163, "๊ฐ€": 164, "์•ต": 165, "๋‹ค": 166, "๊ฐ": 167, "๋ถ™": 168, "๋Ÿญ": 169, "๋ชฐ": 170, "๋ฃฐ": 171, "์งธ": 172, "๋ˆŒ": 173, "๋ฆญ": 174, "ํž˜": 175, "ํŒ": 176, "๊ณก": 177, "๋„˜": 178, "๊ฑฑ": 179, "๊นŠ": 180, "์…œ": 181, "๋ฝ": 182, "์‡ผ": 183, "๋ฅผ": 184, "w": 185, "์ˆœ": 186, "์ดฌ": 187, "๋ฒฝ": 188, "์ฐพ": 189, "ํ‹ฐ": 190, "๋ณด": 191, "๋ฐ•": 192, "๊ทœ": 193, "์šฐ": 194, "์‰ด": 195, "์—ฐ": 196, "์ฐฐ": 197, "์˜ท": 198, "๋Š": 199, "์–ต": 200, "๋ฒ ": 201, "๋ง": 202, "์•ฝ": 203, "์ผ": 204, "๋ฐฑ": 205, "๊ฐ™": 206, "๋ฑ‰": 207, "๋ˆ•": 208, "ํ‹ด": 209, "๋Šฅ": 210, "๊ณ„": 211, "์บ ": 212, "์šธ": 213, "๊ณณ": 214, "๋ฉธ": 215, "๋ถ„": 216, "ํ…ก": 217, "์ถ•": 218, "๋งŒ": 219, "ํ™˜": 220, "์ฑ…": 221, "๋ฏน": 222, "์กฐ": 223, "๋ฉ": 224, "๊ฑท": 225, "๋ฐด": 226, "์ปค": 227, "์•จ": 228, "๋‚ซ": 229, "๋žœ": 230, "๋„": 231, "์ฒ˜": 232, "๋ €": 233, "์น™": 234, "๋—": 235, "ํš": 236, "๋ƒ„": 237, "์›…": 238, "๊ผญ": 239, "์‹": 240, "์‰ฝ": 241, "๋‡Œ": 242, "์ฒจ": 243, "๋ฟ": 244, "ํŒ”": 245, "๋–ค": 246, "์„ญ": 247, "์•Œ": 248, "๋งค": 249, "ํ™ˆ": 250, "๊ดด": 251, "๋™": 252, "์„ธ": 253, "๋ ฅ": 254, "๋–ผ": 255, "๊ด‘": 256, "๋•": 257, "๋…€": 258, "๊ผˆ": 259, "์›ƒ": 260, "๋•…": 261, "๋œ": 262, "์‹ฌ": 263, "ํ†ต": 264, "์ฃ ": 265, "๋Ÿฝ": 266, "๊ฐ”": 267, "์น˜": 268, "์—ญ": 269, "์ฐฝ": 270, "๋ฐ": 271, "๋ฐ–": 272, "ํ‘": 273, "์ฆ˜": 274, "์‚ฌ": 275, "๋‹˜": 276, "์…˜": 277, "ํ‚น": 278, "e": 279, "์‹ ": 280, "๊ฟˆ": 281, "๊ฒฉ": 282, "์ง„": 283, "๋“ฌ": 284, "์ฝฅ": 285, "โ€ข": 286, "์‚ฟ": 287, "์คŒ": 288, "ํ˜„": 289, "๋ฒ”": 290, "๋…น": 291, "์„น": 292, "ํ›จ": 293, "์ฆ": 294, "์ˆฒ": 295, "ํ—ฅ": 296, "๋Œ": 297, "ํ–ฅ": 298, "์ญ‰": 299, "๋ณผ": 300, "๋กœ": 301, "ํ™”": 302, "ํฌ": 303, "ํˆฌ": 304, "๋‹ป": 305, "์žญ": 306, "์Šน": 307, "๊ฐ‘": 308, "์˜": 309, "๋‹": 310, "์€": 311, "์ฒ ": 312, "๋งก": 313, "๊ผฌ": 314, "ํ•จ": 315, "๊ป˜": 316, "ํ˜": 317, "๋ช‡": 318, "๋šซ": 319, "์ฒœ": 320, "๋ผ": 321, "์ฉ": 322, "๋ด": 323, "์˜ฌ": 324, "์Ÿ": 325, "์ฃฝ": 326, "๋•": 327, "ํ–‰": 328, "์ž‘": 329, "์œ„": 330, "์ฒซ": 331, "ํŒ€": 332, "๋ฐ": 333, "ํผ": 334, "์ž˜": 335, "ํ˜•": 336, "๊ฒƒ": 337, "์„ผ": 338, "๊ผฝ": 339, "์”จ": 340, "์ฟ ": 341, "์ฝฉ": 342, "์ฑ„": 343, "๋น„": 344, "ํŒŒ": 345, "ํ•ญ": 346, "๋ƒˆ": 347, "ํžˆ": 348, "๋ฏผ": 349, "๋˜": 350, "์บ„": 351, "๋ฐ": 352, "๋„ˆ": 353, "๋‹ฆ": 354, "์ดŒ": 355, "์ƒต": 356, "ํก": 357, "์ฆˆ": 358, "๋œป": 359, "๋‚€": 360, "ํฌ": 361, "ํ—ค": 362, "๋ฒ…": 363, "๋ ‰": 364, "๊ฝ‰": 365, "๋Š”": 366, "์ €": 367, "๋“œ": 368, "๊ปด": 369, "์ฝœ": 370, "๋–จ": 371, "๋ ‡": 372, "๊ธˆ": 373, "์ ": 374, "์ƒŒ": 375, "ํ’ˆ": 376, "์ƒˆ": 377, "i": 378, "ํƒ": 379, "๋ชจ": 381, "ํ•˜": 382, "๋˜": 383, "์ง": 384, "ํ˜ผ": 385, "์–ด": 386, "๋ก": 387, "ํŽด": 388, "์ข€": 389, "๋ˆˆ": 390, "์Œ": 391, "l": 392, "ํฐ": 393, "์ง€": 394, "์ฆ": 395, "์‚ผ": 396, "๊ถ": 397, "์žŽ": 398, "๋ด": 399, "์•ค": 400, "๋‚ผ": 401, "ํ›„": 402, "๋ผ": 403, "์œ": 404, "๋žญ": 405, "์ƒ‰": 406, "~": 407, "์‚ถ": 408, "ํ† ": 409, "ํŠน": 410, "์กฑ": 411, "์ขŒ": 412, "ํ™‹": 413, "์ ": 414, "๋‹ญ": 415, "์—…": 416, "๋“ฏ": 417, "๋ฉค": 418, "๋‹Œ": 419, "ํด": 420, "์ˆ˜": 421, "์พŒ": 422, "๋‹": 423, "๋ฅ ": 424, "ํ“จ": 425, "์œผ": 426, "์น ": 427, "์™„": 428, "์ž”": 429, "ํ’‹": 430, "๋ฆ‡": 431, "๊ฒฝ": 432, "r": 433, "๋†€": 434, "๋‹ฌ": 435, "์—‡": 436, "๊ตฝ": 437, "๋‘": 438, "ํ™": 439, "๊นจ": 440, "์ฏค": 441, "ํ˜ธ": 442, "๋ฒˆ": 443, "์กŒ": 444, "ํ—Œ": 445, "์ซ“": 446, "์ตœ": 447, "์นด": 448, "๊ฐฏ": 449, "ํŒจ": 450, "๋”": 451, "์ˆจ": 452, "ํ•œ": 453, "์จ": 454, "๋ฐฅ": 455, "์ผ„": 456, "๋ฝ": 457, "์‹ถ": 458, "๋œจ": 459, "๋„": 460, "ํ•‘": 461, "ํŽœ": 462, "์ทจ": 463, "๋ณต": 464, "ํ‘ธ": 465, "๊ตฌ": 466, "๋น›": 467, "์˜ฎ": 468, "๊ทผ": 469, "๋ธŒ": 470, "๋ฌด": 471, "๊ท€": 472, "์ผœ": 473, "์ง“": 474, "ํฐ": 475, "์—”": 476, "ํƒ‘": 477, "ํ˜": 478, "ํž": 479, "๋ฆผ": 480, "n": 481, "๋†“": 482, "๋ง›": 483, "๋ฃŒ": 484, "๋‚จ": 485, "์•…": 486, "๋กฏ": 487, "์ฆ‰": 488, "ํ‚จ": 489, "๋‚ธ": 490, "๋ˆ„": 491, "์™”": 492, "๋„‰": 493, "์•”": 494, "๋ฅด": 495, "๋ฐ›": 496, "์žฐ": 497, "๊ธธ": 498, "์ˆซ": 499, "๋…ธ": 500, "๋ฉง": 501, "๋‚œ": 502, "ํŽผ": 503, "์™ผ": 504, "์ธ ": 505, "์› ": 506, "ํด": 507, "๋ฃจ": 508, "๋’ท": 509, "์ž ": 510, "๋Ÿฐ": 511, "๊ฐ‡": 512, "์˜†": 513, "๊ถŒ": 514, "๋ฐ˜": 515, "์…ฐ": 516, "ํ•ธ": 517, "์บ”": 518, "ํ™•": 519, "์›น": 520, "์ถฐ": 521, "์œฝ": 522, "๋ฎ": 523, "a": 524, "๊ฒฌ": 525, "๊ปŒ": 526, "์…€": 527, "๋ฆด": 528, "๋›ฐ": 529, "๋ž˜": 530, "์ผฐ": 531, "์Šต": 532, "g": 533, "๋ฐ€": 534, "๋ฉฐ": 535, "ํ”Œ": 536, "m": 537, "์•Š": 538, "์‘": 539, "์ ธ": 540, "๋‚ฎ": 541, "์ฉ": 542, "์Šค": 543, "์—„": 544, "์•ฑ": 545, "๊น”": 546, "๋“": 547, "๋‚ ": 548, "์›Œ": 549, "ํ–‡": 550, "์…จ": 551, "๊ฑฐ": 552, "์žฆ": 553, "์นผ": 554, "ใ„น": 555, "๊ฐ": 556, "์„ ": 557, "๋”ฐ": 558, "๋ž": 559, "๋ผ": 560, "๋‘˜": 561, "๊ฐ–": 562, "๋ ˆ": 563, "๋ฒ•": 564, "์ฃผ": 565, "์งฆ": 566, "์ฐ": 567, "5": 568, "์š•": 569, "๊ตด": 570, "์ธต": 571, "ํƒ": 572, "์ดˆ": 573, "h": 574, "๋ฅ˜": 575, "๋Œ„": 576, "ํœด": 577, "z": 578, "๋…„": 579, "๋ป—": 580, "๊น": 581, "ใ„ด": 582, "๋„ฃ": 583, "์˜": 584, "ํŠœ": 585, "์ฒ™": 586, "๋งŽ": 587, "ํ””": 588, "๋ฉ‹": 589, "ํ": 590, "๋Ÿฌ": 591, "ํšจ": 592, "๋จ": 593, "์บฃ": 594, "์‰ผ": 595, "๊ฒฐ": 596, "์šฉ": 597, "โ€‹": 598, "๋ง": 599, "๋Ÿ‰": 600, "๋Šฆ": 601, "๋ฉ€": 602, "์บ‡": 603, "์‹ซ": 604, "๋ฏธ": 605, "๊น": 606, "์ ˆ": 607, "๊ตญ": 608, "๋‚ด": 609, "๊ต‰": 610, "์ถฉ": 611, "์••": 612, "๋‚™": 613, "x": 614, "์ถ”": 615, "ํ’": 616, "ํ–ˆ": 617, "ํ—˜": 618, "ํ›ˆ": 619, "๋‹ˆ": 620, "ํ…Œ": 621, "6": 622, "์ถค": 623, "๊ด€": 624, "์—ฌ": 625, "๋”": 626, "์ชฝ": 627, "์˜ˆ": 628, "์žก": 629, "์‹ค": 630, "๋‚ณ": 631, "๋นจ": 632, "์žŠ": 633, "j": 634, "ํ•ฉ": 635, "์ฒต": 636, "์‚ฐ": 637, "ํŒ": 638, "ํŽธ": 639, "๋žŒ": 640, "๋”ฉ": 641, "์ค": 642, "๋””": 643, "ํ„ด": 644, "๋ฐฐ": 645, "์ฝ˜": 646, "์…”": 647, "์žˆ": 648, "๋ฆฌ": 649, "์‡ ": 650, "์ „": 651, "์ ": 652, "์–ป": 653, "๋€Œ": 654, "๊ตฐ": 655, "ํƒ“": 656, "ํ‹ฑ": 657, "๋˜": 658, "์ผ": 659, "์„ฌ": 660, "์‹ธ": 661, "์†": 662, "ํŽ„": 663, "๊บผ": 664, "์”ฉ": 665, "๋ž€": 666, "๊ณผ": 667, "์›": 668, "์Œ“": 669, "๋ฆŽ": 670, "์ปด": 671, "๋งž": 672, "์ด": 673, "์”น": 674, "๋ฉด": 675, "์›”": 676, "๋…ผ": 677, "ํ”": 678, "์•ก": 679, "ํญ": 680, "๊ฒ€": 681, "๊ฐ": 682, "์›€": 683, "์„ฑ": 684, "์ง‘": 685, "๊ฐˆ": 686, "์ข‹": 687, "์ฉŒ": 688, "๋‚„": 689, "๋‚ฌ": 690, "๊ตฟ": 691, "ํ": 692, "ํผ": 693, "ํƒ": 694, "k": 695, "๋‘ ": 696, "์ •": 697, "๋ณ„": 698, "๋ฐค": 699, "๋‹ณ": 700, "๋ค": 701, "ํ…": 702, "8": 703, "์ƒ": 704, "์งœ": 705, "๋จผ": 706, "ํ˜‘": 707, "์„ค": 708, "์•—": 709, "ํƒ”": 710, "๋ชน": 711, "๋‹ฅ": 712, "2": 713, "๋Œ": 714, "์›ฐ": 715, "๋จธ": 716, "์•ˆ": 717, "๊นŒ": 718, "์ฐฉ": 719, "4": 720, "์ฝ”": 721, "์ปน": 722, "์„": 723, "๋”ฑ": 724, "0": 725, "๋“ค": 726, "๋ ": 727, "๋ น": 728, "๋ชฉ": 729, "์ผ€": 730, "u": 731, "๋‹ฎ": 732, "์„ž": 733, "ํƒ€": 734, "๋ฌธ": 735, "๋ฃธ": 736, "์‡„": 737, "์นœ": 738, "๊ผฐ": 739, "๋ฟŒ": 740, "๋ž": 741, "๋ฐญ": 742, "๋ฉ•": 743, "๋‹ซ": 744, "๋ถ€": 745, "๊ธ‰": 746, "์‹œ": 747, "์ฐฌ": 748, "๊ฒ": 749, "o": 750, "์—ˆ": 751, "์จ": 752, "9": 753, "์ฟค": 754, "๋Ÿด": 755, "๋ชฝ": 756, "๋ฅธ": 757, "์ฅ": 758, "๋ณ€": 759, "๋ธ": 760, "๋ฒจ": 761, "์ง": 762, "๋ ด": 763, "์—†": 764, "์Šท": 765, "ํ‚ฌ": 766, "์Šฌ": 767, "๋˜‘": 768, "๋นŒ": 769, "์–ผ": 770, "์ฐŒ": 771, "๋ ธ": 772, "t": 773, "ํ—ท": 774, "์–‘": 775, "์•ž": 776, "๋ฐŒ": 777, "๋ฐ”": 778, "์™ธ": 779, "ใ…†": 780, "๊น€": 781, "์œจ": 782, "์•‰": 783, "๋ง‰": 784, "๋ฉ": 785, "v": 786, "์‘ฅ": 787, "ํ˜€": 788, "๋ฏฟ": 789, "๊ฐœ": 790, "๋ขฐ": 791, "์ปฌ": 792, "๋ ค": 793, "ํ—ฌ": 794, "๋„“": 795, "๋‘ฅ": 796, "์•ผ": 797, "๋ฐฉ": 798, "์นจ": 799, "ํ™œ": 800, "์ฑ™": 801, "๊ณ ": 802, "๊ถ": 803, "๋ด‰": 804, "ํ„ธ": 805, "๊ณต": 806, "๊ธฐ": 807, "๊นŽ": 808, "๋ฌผ": 809, "๋ฐœ": 810, "์˜ต": 811, "๋น…": 812, "๊ฐ„": 813, "๋ก€": 814, "์• ": 815, "ํšŸ": 816, "๊ทธ": 817, "๋œ": 818, "๊ฒŸ": 819, "๋ฆฟ": 820, "๊ฟ”": 821, "๊ธ€": 822, "์ข…": 823, "์ƒ": 824, "์‰ฌ": 825, "์™œ": 826, "์“ฐ": 827, "๋ˆ": 828, "ํ…": 829, "ํƒ ": 830, "๋ฌต": 831, "์ƒค": 832, "๋Š˜": 833, "๋ƒฅ": 834, "๋": 835, "๊ฒผ": 836, "์ธก": 837, "๋ ›": 838, "๋กญ": 839, "์ž„": 840, "๋‹ด": 841, "ํ˜น": 842, "๋ˆ…": 843, "์„œ": 844, "๋‹น": 845, "๋จน": 846, "f": 847, "์งŠ": 848, "๋ƒ…": 849, "๋ฒŒ": 850, "์˜ค": 851, "ํ’€": 852, "ํ•„": 853, "์งง": 854, "์†": 855, "๋†’": 856, "๋•Œ": 857, "์บ": 858, "๋žฌ": 859, "๋ฆ‰": 860, "๋ฃน": 861, "๋ Œ": 862, "๋‚": 863, "์ž…": 864, "๋„ท": 865, "์กด": 866, "๋ชฌ": 867, "๋ฑ…": 868, "์ฝ": 869, "์ž": 870, "๋žต": 871, "์†ก": 872, "์–ธ": 873, "์š”": 874, "์ณ": 875, "ํ‡ด": 876, "๋ชธ": 877, "d": 878, "s": 879, "์ถœ": 880, "์ฐธ": 881, "๊ธ": 882, "๊ฑธ": 883, "๋งป": 884, "๊ณง": 885, "๋œฐ": 886, "์ƒ˜": 887, "3": 888, "๋ฝ": 889, "์ˆ™": 890, "์ฐจ": 891, "๋– ": 892, "ํ…œ": 893, "์‹ผ": 894, "ํ‰": 895, "๋ž‘": 896, "์—ผ": 897, "๋ฉ”": 898, "ํŽ˜": 899, "ใ…": 900, "์นญ": 901, "๋ฒ„": 902, "๋ฒค": 903, "๋ง": 904, "ํ‚ค": 905, "๋ฐ‘": 906, "๋ฆ„": 907, "์ถฅ": 908, "์ ‘": 909, "ํ”ˆ": 910, "๋ ต": 911, "์žฌ": 912, "์ปจ": 913, "์„": 914, "๊ฟ€": 915, "๋ฐ": 916, "๊ฒŒ": 917, "์•˜": 918, "|": 380, "[UNK]": 919, "[PAD]": 920}