Doogie commited on
Commit
f71251e
โ€ข
1 Parent(s): c83e73d

add tokenizer

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