add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- 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 |
+
{"๋": 0, "ํ": 1, "๋น ": 2, "์": 3, "์ค": 4, "๋ฃ": 5, "๋น": 6, "๋จ": 7, "๊ด": 8, "๋ต": 9, "ํ ": 10, "์": 11, "๋ถ": 12, "๋ณ": 13, "๋จ": 14, "๋ด": 15, "๋ฟ": 16, "ํด": 17, "๊ฐ": 18, "์ชผ": 19, "ํ": 20, "๋ทฐ": 21, "๋ชป": 22, "๋": 23, "๋
": 24, "๊ทน": 25, "ํฌ": 26, "์ธ": 27, "์ ": 28, "๋ฝ": 29, "์ค": 30, "์": 31, "์งค": 32, "๊ฒช": 33, "๋งจ": 34, "์ฐฎ": 35, "์ค": 36, "๋ฑ": 37, "๋ฃฌ": 38, "์ด": 39, "๋ง": 40, "ํด": 41, "ํ
ฌ": 42, "ํฌ": 43, "๋ด": 44, "๋ป": 45, "์ง": 46, "ํ": 47, "q": 48, "ํ": 49, "์ง": 50, "์": 51, "์ด": 52, "์": 53, "์ก": 54, "ํ
": 55, "์ผ": 56, "๊ณค": 57, "๋": 58, "๋น": 59, "๋ฉ": 60, "๊ต": 61, "์ต": 62, "ํ": 63, "ํจ": 64, "์ญ": 65, "์ฒญ": 66, "ํ": 67, "์จ": 68, "ํ": 69, "์ฑ": 70, "๊ด": 71, "๋ฆฐ": 72, "์ธ": 73, "์ปธ": 74, "ํ": 75, "๋ฌป": 76, "ํฐ": 77, "๋น": 78, "๋ก ": 79, "์": 80, "๋น": 81, "์": 82, "๋ธ": 83, "ํผ": 84, "๋ง": 85, "๋
": 86, "7": 87, "์ด": 88, "๋ถ": 89, "y": 90, "c": 91, "ํ": 92, "ํ": 93, "๋": 94, "์ฝ": 95, "ํฑ": 96, "์ฅ": 97, "์ ": 98, "์ ": 99, "๊ณจ": 100, "p": 101, "๋ค": 102, "์": 103, "๊ฑด": 104, "ํ": 105, "์": 106, "๊ธ": 107, "์": 108, "1": 109, "๋ ": 110, "์": 111, "๋ช
": 112, "ํ": 113, "ํธ": 114, "๋ช": 115, "๋ฆฝ": 116, "๋
": 117, "ใ
": 118, "ํ": 119, "๋": 120, "๋ณธ": 121, "์": 122, "๋ผ": 123, "๋ด": 124, "b": 125, "๋": 126, "์ด": 127, "๊ฒจ": 128, "๋ จ": 129, "๋ฉ": 130, "๋ค": 131, "๋ฒ": 132, "์ ค": 133, "๋ฌ": 134, "ํค": 135, "๊ณฐ": 136, "์ฌ": 137, "๋": 138, "์ฝค": 139, "์
": 140, "๋งฅ": 141, "์จ": 142, "๋ ": 143, "๋ฆ
": 144, "์ฒด": 145, "์จ": 146, "์น": 147, "์ฟผ": 148, "์จ": 149, "๋ฉ": 150, "๊ฝค": 151, "์": 152, "๊พธ": 153, "์ง": 154, "๊ฒ ": 155, "ํฉ": 156, "์ค": 157, "ํฅ": 158, "์ ": 159, "๊ท ": 160, "๊ธด": 161, "๋ญ": 162, "์ ": 163, "๊ฐ": 164, "์ต": 165, "๋ค": 166, "๊ฐ": 167, "๋ถ": 168, "๋ญ": 169, "๋ชฐ": 170, "๋ฃฐ": 171, "์งธ": 172, "๋": 173, "๋ฆญ": 174, "ํ": 175, "ํ": 176, "๊ณก": 177, "๋": 178, "๊ฑฑ": 179, "๊น": 180, "์
": 181, "๋ฝ": 182, "์ผ": 183, "๋ฅผ": 184, "w": 185, "์": 186, "์ดฌ": 187, "๋ฒฝ": 188, "์ฐพ": 189, "ํฐ": 190, "๋ณด": 191, "๋ฐ": 192, "๊ท": 193, "์ฐ": 194, "์ด": 195, "์ฐ": 196, "์ฐฐ": 197, "์ท": 198, "๋": 199, "์ต": 200, "๋ฒ ": 201, "๋ง": 202, "์ฝ": 203, "์ผ": 204, "๋ฐฑ": 205, "๊ฐ": 206, "๋ฑ": 207, "๋": 208, "ํด": 209, "๋ฅ": 210, "๊ณ": 211, "์บ ": 212, "์ธ": 213, "๊ณณ": 214, "๋ฉธ": 215, "๋ถ": 216, "ํ
ก": 217, "์ถ": 218, "๋ง": 219, "ํ": 220, "์ฑ
": 221, "๋ฏน": 222, "์กฐ": 223, "๋ฉ": 224, "๊ฑท": 225, "๋ฐด": 226, "์ปค": 227, "์จ": 228, "๋ซ": 229, "๋": 230, "๋": 231, "์ฒ": 232, "๋ ": 233, "์น": 234, "๋": 235, "ํ": 236, "๋": 237, "์
": 238, "๊ผญ": 239, "์": 240, "์ฝ": 241, "๋": 242, "์ฒจ": 243, "๋ฟ": 244, "ํ": 245, "๋ค": 246, "์ญ": 247, "์": 248, "๋งค": 249, "ํ": 250, "๊ดด": 251, "๋": 252, "์ธ": 253, "๋ ฅ": 254, "๋ผ": 255, "๊ด": 256, "๋": 257, "๋
": 258, "๊ผ": 259, "์": 260, "๋
": 261, "๋": 262, "์ฌ": 263, "ํต": 264, "์ฃ ": 265, "๋ฝ": 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, "๊ฟ": 281, "๊ฒฉ": 282, "์ง": 283, "๋ฌ": 284, "์ฝฅ": 285, "โข": 286, "์ฟ": 287, "์ค": 288, "ํ": 289, "๋ฒ": 290, "๋
น": 291, "์น": 292, "ํจ": 293, "์ฆ": 294, "์ฒ": 295, "ํฅ": 296, "๋": 297, "ํฅ": 298, "์ญ": 299, "๋ณผ": 300, "๋ก": 301, "ํ": 302, "ํฌ": 303, "ํฌ": 304, "๋ป": 305, "์ญ": 306, "์น": 307, "๊ฐ": 308, "์": 309, "๋": 310, "์": 311, "์ฒ ": 312, "๋งก": 313, "๊ผฌ": 314, "ํจ": 315, "๊ป": 316, "ํ": 317, "๋ช": 318, "๋ซ": 319, "์ฒ": 320, "๋ผ": 321, "์ฉ": 322, "๋ด": 323, "์ฌ": 324, "์": 325, "์ฃฝ": 326, "๋": 327, "ํ": 328, "์": 329, "์": 330, "์ฒซ": 331, "ํ": 332, "๋ฐ": 333, "ํผ": 334, "์": 335, "ํ": 336, "๊ฒ": 337, "์ผ": 338, "๊ผฝ": 339, "์จ": 340, "์ฟ ": 341, "์ฝฉ": 342, "์ฑ": 343, "๋น": 344, "ํ": 345, "ํญ": 346, "๋": 347, "ํ": 348, "๋ฏผ": 349, "๋": 350, "์บ": 351, "๋ฐ": 352, "๋": 353, "๋ฆ": 354, "์ด": 355, "์ต": 356, "ํก": 357, "์ฆ": 358, "๋ป": 359, "๋": 360, "ํฌ": 361, "ํค": 362, "๋ฒ
": 363, "๋ ": 364, "๊ฝ": 365, "๋": 366, "์ ": 367, "๋": 368, "๊ปด": 369, "์ฝ": 370, "๋จ": 371, "๋ ": 372, "๊ธ": 373, "์ ": 374, "์": 375, "ํ": 376, "์": 377, "i": 378, "ํ": 379, "๋ชจ": 381, "ํ": 382, "๋": 383, "์ง": 384, "ํผ": 385, "์ด": 386, "๋ก": 387, "ํด": 388, "์ข": 389, "๋": 390, "์": 391, "l": 392, "ํฐ": 393, "์ง": 394, "์ฆ": 395, "์ผ": 396, "๊ถ": 397, "์": 398, "๋ด": 399, "์ค": 400, "๋ผ": 401, "ํ": 402, "๋ผ": 403, "์": 404, "๋ญ": 405, "์": 406, "~": 407, "์ถ": 408, "ํ ": 409, "ํน": 410, "์กฑ": 411, "์ข": 412, "ํ": 413, "์ ": 414, "๋ญ": 415, "์
": 416, "๋ฏ": 417, "๋ฉค": 418, "๋": 419, "ํด": 420, "์": 421, "์พ": 422, "๋": 423, "๋ฅ ": 424, "ํจ": 425, "์ผ": 426, "์น ": 427, "์": 428, "์": 429, "ํ": 430, "๋ฆ": 431, "๊ฒฝ": 432, "r": 433, "๋": 434, "๋ฌ": 435, "์": 436, "๊ตฝ": 437, "๋": 438, "ํ": 439, "๊นจ": 440, "์ฏค": 441, "ํธ": 442, "๋ฒ": 443, "์ก": 444, "ํ": 445, "์ซ": 446, "์ต": 447, "์นด": 448, "๊ฐฏ": 449, "ํจ": 450, "๋": 451, "์จ": 452, "ํ": 453, "์จ": 454, "๋ฐฅ": 455, "์ผ": 456, "๋ฝ": 457, "์ถ": 458, "๋จ": 459, "๋": 460, "ํ": 461, "ํ": 462, "์ทจ": 463, "๋ณต": 464, "ํธ": 465, "๊ตฌ": 466, "๋น": 467, "์ฎ": 468, "๊ทผ": 469, "๋ธ": 470, "๋ฌด": 471, "๊ท": 472, "์ผ": 473, "์ง": 474, "ํฐ": 475, "์": 476, "ํ": 477, "ํ": 478, "ํ": 479, "๋ฆผ": 480, "n": 481, "๋": 482, "๋ง": 483, "๋ฃ": 484, "๋จ": 485, "์
": 486, "๋กฏ": 487, "์ฆ": 488, "ํจ": 489, "๋ธ": 490, "๋": 491, "์": 492, "๋": 493, "์": 494, "๋ฅด": 495, "๋ฐ": 496, "์ฐ": 497, "๊ธธ": 498, "์ซ": 499, "๋
ธ": 500, "๋ฉง": 501, "๋": 502, "ํผ": 503, "์ผ": 504, "์ธ ": 505, "์ ": 506, "ํด": 507, "๋ฃจ": 508, "๋ท": 509, "์ ": 510, "๋ฐ": 511, "๊ฐ": 512, "์": 513, "๊ถ": 514, "๋ฐ": 515, "์
ฐ": 516, "ํธ": 517, "์บ": 518, "ํ": 519, "์น": 520, "์ถฐ": 521, "์ฝ": 522, "๋ฎ": 523, "a": 524, "๊ฒฌ": 525, "๊ป": 526, "์
": 527, "๋ฆด": 528, "๋ฐ": 529, "๋": 530, "์ผฐ": 531, "์ต": 532, "g": 533, "๋ฐ": 534, "๋ฉฐ": 535, "ํ": 536, "m": 537, "์": 538, "์": 539, "์ ธ": 540, "๋ฎ": 541, "์ฉ": 542, "์ค": 543, "์": 544, "์ฑ": 545, "๊น": 546, "๋": 547, "๋ ": 548, "์": 549, "ํ": 550, "์
จ": 551, "๊ฑฐ": 552, "์ฆ": 553, "์นผ": 554, "ใน": 555, "๊ฐ": 556, "์ ": 557, "๋ฐ": 558, "๋": 559, "๋ผ": 560, "๋": 561, "๊ฐ": 562, "๋ ": 563, "๋ฒ": 564, "์ฃผ": 565, "์งฆ": 566, "์ฐ": 567, "5": 568, "์": 569, "๊ตด": 570, "์ธต": 571, "ํ": 572, "์ด": 573, "h": 574, "๋ฅ": 575, "๋": 576, "ํด": 577, "z": 578, "๋
": 579, "๋ป": 580, "๊น": 581, "ใด": 582, "๋ฃ": 583, "์": 584, "ํ": 585, "์ฒ": 586, "๋ง": 587, "ํ": 588, "๋ฉ": 589, "ํ": 590, "๋ฌ": 591, "ํจ": 592, "๋จ": 593, "์บฃ": 594, "์ผ": 595, "๊ฒฐ": 596, "์ฉ": 597, "โ": 598, "๋ง": 599, "๋": 600, "๋ฆ": 601, "๋ฉ": 602, "์บ": 603, "์ซ": 604, "๋ฏธ": 605, "๊น": 606, "์ ": 607, "๊ตญ": 608, "๋ด": 609, "๊ต": 610, "์ถฉ": 611, "์": 612, "๋": 613, "x": 614, "์ถ": 615, "ํ": 616, "ํ": 617, "ํ": 618, "ํ": 619, "๋": 620, "ํ
": 621, "6": 622, "์ถค": 623, "๊ด": 624, "์ฌ": 625, "๋": 626, "์ชฝ": 627, "์": 628, "์ก": 629, "์ค": 630, "๋ณ": 631, "๋นจ": 632, "์": 633, "j": 634, "ํฉ": 635, "์ฒต": 636, "์ฐ": 637, "ํ": 638, "ํธ": 639, "๋": 640, "๋ฉ": 641, "์ค": 642, "๋": 643, "ํด": 644, "๋ฐฐ": 645, "์ฝ": 646, "์
": 647, "์": 648, "๋ฆฌ": 649, "์ ": 650, "์ ": 651, "์ ": 652, "์ป": 653, "๋": 654, "๊ตฐ": 655, "ํ": 656, "ํฑ": 657, "๋": 658, "์ผ": 659, "์ฌ": 660, "์ธ": 661, "์": 662, "ํ": 663, "๊บผ": 664, "์ฉ": 665, "๋": 666, "๊ณผ": 667, "์": 668, "์": 669, "๋ฆ": 670, "์ปด": 671, "๋ง": 672, "์ด": 673, "์น": 674, "๋ฉด": 675, "์": 676, "๋
ผ": 677, "ํ": 678, "์ก": 679, "ํญ": 680, "๊ฒ": 681, "๊ฐ": 682, "์": 683, "์ฑ": 684, "์ง": 685, "๊ฐ": 686, "์ข": 687, "์ฉ": 688, "๋": 689, "๋ฌ": 690, "๊ตฟ": 691, "ํ": 692, "ํผ": 693, "ํ": 694, "k": 695, "๋ ": 696, "์ ": 697, "๋ณ": 698, "๋ฐค": 699, "๋ณ": 700, "๋ค": 701, "ํ
": 702, "8": 703, "์": 704, "์ง": 705, "๋จผ": 706, "ํ": 707, "์ค": 708, "์": 709, "ํ": 710, "๋ชน": 711, "๋ฅ": 712, "2": 713, "๋": 714, "์ฐ": 715, "๋จธ": 716, "์": 717, "๊น": 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, "์": 733, "ํ": 734, "๋ฌธ": 735, "๋ฃธ": 736, "์": 737, "์น": 738, "๊ผฐ": 739, "๋ฟ": 740, "๋": 741, "๋ฐญ": 742, "๋ฉ": 743, "๋ซ": 744, "๋ถ": 745, "๊ธ": 746, "์": 747, "์ฐฌ": 748, "๊ฒ": 749, "o": 750, "์": 751, "์จ": 752, "9": 753, "์ฟค": 754, "๋ด": 755, "๋ชฝ": 756, "๋ฅธ": 757, "์ฅ": 758, "๋ณ": 759, "๋ธ": 760, "๋ฒจ": 761, "์ง": 762, "๋ ด": 763, "์": 764, "์ท": 765, "ํฌ": 766, "์ฌ": 767, "๋": 768, "๋น": 769, "์ผ": 770, "์ฐ": 771, "๋ ธ": 772, "t": 773, "ํท": 774, "์": 775, "์": 776, "๋ฐ": 777, "๋ฐ": 778, "์ธ": 779, "ใ
": 780, "๊น": 781, "์จ": 782, "์": 783, "๋ง": 784, "๋ฉ": 785, "v": 786, "์ฅ": 787, "ํ": 788, "๋ฏฟ": 789, "๊ฐ": 790, "๋ขฐ": 791, "์ปฌ": 792, "๋ ค": 793, "ํฌ": 794, "๋": 795, "๋ฅ": 796, "์ผ": 797, "๋ฐฉ": 798, "์นจ": 799, "ํ": 800, "์ฑ": 801, "๊ณ ": 802, "๊ถ": 803, "๋ด": 804, "ํธ": 805, "๊ณต": 806, "๊ธฐ": 807, "๊น": 808, "๋ฌผ": 809, "๋ฐ": 810, "์ต": 811, "๋น
": 812, "๊ฐ": 813, "๋ก": 814, "์ ": 815, "ํ": 816, "๊ทธ": 817, "๋": 818, "๊ฒ": 819, "๋ฆฟ": 820, "๊ฟ": 821, "๊ธ": 822, "์ข
": 823, "์": 824, "์ฌ": 825, "์": 826, "์ฐ": 827, "๋": 828, "ํ
": 829, "ํ ": 830, "๋ฌต": 831, "์ค": 832, "๋": 833, "๋ฅ": 834, "๋": 835, "๊ฒผ": 836, "์ธก": 837, "๋ ": 838, "๋กญ": 839, "์": 840, "๋ด": 841, "ํน": 842, "๋
": 843, "์": 844, "๋น": 845, "๋จน": 846, "f": 847, "์ง": 848, "๋
": 849, "๋ฒ": 850, "์ค": 851, "ํ": 852, "ํ": 853, "์งง": 854, "์": 855, "๋": 856, "๋": 857, "์บ": 858, "๋ฌ": 859, "๋ฆ": 860, "๋ฃน": 861, "๋ ": 862, "๋": 863, "์
": 864, "๋ท": 865, "์กด": 866, "๋ชฌ": 867, "๋ฑ
": 868, "์ฝ": 869, "์": 870, "๋ต": 871, "์ก": 872, "์ธ": 873, "์": 874, "์ณ": 875, "ํด": 876, "๋ชธ": 877, "d": 878, "s": 879, "์ถ": 880, "์ฐธ": 881, "๊ธ": 882, "๊ฑธ": 883, "๋งป": 884, "๊ณง": 885, "๋ฐ": 886, "์": 887, "3": 888, "๋ฝ": 889, "์": 890, "์ฐจ": 891, "๋ ": 892, "ํ
": 893, "์ผ": 894, "ํ": 895, "๋": 896, "์ผ": 897, "๋ฉ": 898, "ํ": 899, "ใ
": 900, "์นญ": 901, "๋ฒ": 902, "๋ฒค": 903, "๋ง": 904, "ํค": 905, "๋ฐ": 906, "๋ฆ": 907, "์ถฅ": 908, "์ ": 909, "ํ": 910, "๋ ต": 911, "์ฌ": 912, "์ปจ": 913, "์": 914, "๊ฟ": 915, "๋ฐ": 916, "๊ฒ": 917, "์": 918, "|": 380, "[UNK]": 919, "[PAD]": 920}
|