add tokenizer
02697c4
|
{ |
|
"[PAD]": 507, |
|
"[UNK]": 506, |
|
"|": 0, |
|
"ใฑ": 1, |
|
"ใด": 2, |
|
"ใท": 3, |
|
"ใน": 4, |
|
"ใ
": 5, |
|
"ใ
": 6, |
|
"๊ฐ": 7, |
|
"๊ฐ": 8, |
|
"๊ฐ": 9, |
|
"๊ฐ": 10, |
|
"๊ฐ": 11, |
|
"๊ฐ": 12, |
|
"๊ฐ": 13, |
|
"๊ฐ": 14, |
|
"๊ฐ": 15, |
|
"๊ฐ": 16, |
|
"๊ฐ": 17, |
|
"๊ฐฏ": 18, |
|
"๊ฑฐ": 19, |
|
"๊ฑด": 20, |
|
"๊ฑธ": 21, |
|
"๊ฒ": 22, |
|
"๊ฒ": 23, |
|
"๊ฒ": 24, |
|
"๊ฒ": 25, |
|
"๊ฒ ": 26, |
|
"๊ฒจ": 27, |
|
"๊ฒฐ": 28, |
|
"๊ฒฝ": 29, |
|
"๊ณ": 30, |
|
"๊ณ ": 31, |
|
"๊ณก": 32, |
|
"๊ณค": 33, |
|
"๊ณจ": 34, |
|
"๊ณฑ": 35, |
|
"๊ณณ": 36, |
|
"๊ณต": 37, |
|
"๊ณผ": 38, |
|
"๊ด": 39, |
|
"๊ต": 40, |
|
"๊ต": 41, |
|
"๊ตฌ": 42, |
|
"๊ตญ": 43, |
|
"๊ตณ": 44, |
|
"๊ถ": 45, |
|
"๊ท": 46, |
|
"๊ท": 47, |
|
"๊ท": 48, |
|
"๊ทธ": 49, |
|
"๊ทผ": 50, |
|
"๊ทฟ": 51, |
|
"๊ธ": 52, |
|
"๊ธ": 53, |
|
"๊ธฐ": 54, |
|
"๊ธด": 55, |
|
"๊ธธ": 56, |
|
"๊น": 57, |
|
"๊น": 58, |
|
"๊น": 59, |
|
"๊นฅ": 60, |
|
"๊บผ": 61, |
|
"๊ป": 62, |
|
"๊ป": 63, |
|
"๊ผญ": 64, |
|
"๊ผผ": 65, |
|
"๊พธ": 66, |
|
"๊พผ": 67, |
|
"๊ฟ": 68, |
|
"๋": 69, |
|
"๋": 70, |
|
"๋": 71, |
|
"๋": 72, |
|
"๋ผ": 73, |
|
"๋": 74, |
|
"๋": 75, |
|
"๋ ": 76, |
|
"๋ฉ": 77, |
|
"๋ซ": 78, |
|
"๋ฌ": 79, |
|
"๋ฎ": 80, |
|
"๋ด": 81, |
|
"๋ธ": 82, |
|
"๋ผ": 83, |
|
"๋": 84, |
|
"๋": 85, |
|
"๋": 86, |
|
"๋": 87, |
|
"๋ฃ": 88, |
|
"๋ค": 89, |
|
"๋ท": 90, |
|
"๋
": 91, |
|
"๋
": 92, |
|
"๋
น": 93, |
|
"๋": 94, |
|
"๋": 95, |
|
"๋": 96, |
|
"๋จ": 97, |
|
"๋": 98, |
|
"๋": 99, |
|
"๋": 100, |
|
"๋": 101, |
|
"๋": 102, |
|
"๋": 103, |
|
"๋": 104, |
|
"๋": 105, |
|
"๋": 106, |
|
"๋ค": 107, |
|
"๋จ": 108, |
|
"๋ฌ": 109, |
|
"๋ด": 110, |
|
"๋ต": 111, |
|
"๋ท": 112, |
|
"๋น": 113, |
|
"๋": 114, |
|
"๋": 115, |
|
"๋": 116, |
|
"๋ฉ": 117, |
|
"๋ฐ": 118, |
|
"๋ธ": 119, |
|
"๋": 120, |
|
"๋": 121, |
|
"๋": 122, |
|
"๋ผ": 123, |
|
"๋": 124, |
|
"๋": 125, |
|
"๋": 126, |
|
"๋ ": 127, |
|
"๋ฉ": 128, |
|
"๋": 129, |
|
"๋": 130, |
|
"๋": 131, |
|
"๋ฌ": 132, |
|
"๋ท": 133, |
|
"๋": 134, |
|
"๋ ": 135, |
|
"๋ค": 136, |
|
"๋ฑ": 137, |
|
"๋": 138, |
|
"๋ฐ": 139, |
|
"๋": 140, |
|
"๋": 141, |
|
"๋ ": 142, |
|
"๋ค": 143, |
|
"๋จ": 144, |
|
"๋ป": 145, |
|
"๋": 146, |
|
"๋": 147, |
|
"๋จ": 148, |
|
"๋ป": 149, |
|
"๋": 150, |
|
"๋ผ": 151, |
|
"๋": 152, |
|
"๋": 153, |
|
"๋": 154, |
|
"๋": 155, |
|
"๋": 156, |
|
"๋": 157, |
|
"๋ฌ": 158, |
|
"๋": 159, |
|
"๋ฌ": 160, |
|
"๋ฐ": 161, |
|
"๋ด": 162, |
|
"๋ผ": 163, |
|
"๋ ": 164, |
|
"๋ ": 165, |
|
"๋ ": 166, |
|
"๋ ค": 167, |
|
"๋ ฅ": 168, |
|
"๋ จ": 169, |
|
"๋ ธ": 170, |
|
"๋ก": 171, |
|
"๋ก": 172, |
|
"๋ก": 173, |
|
"๋ก ": 174, |
|
"๋ฃ": 175, |
|
"๋ฃจ": 176, |
|
"๋ฅ": 177, |
|
"๋ฅด": 178, |
|
"๋ฅธ": 179, |
|
"๋ฅผ": 180, |
|
"๋ฆ": 181, |
|
"๋ฆฌ": 182, |
|
"๋ฆฐ": 183, |
|
"๋ฆผ": 184, |
|
"๋ฆฝ": 185, |
|
"๋ง": 186, |
|
"๋ง": 187, |
|
"๋ง": 188, |
|
"๋ง": 189, |
|
"๋ง": 190, |
|
"๋ง": 191, |
|
"๋ง": 192, |
|
"๋งก": 193, |
|
"๋งค": 194, |
|
"๋งบ": 195, |
|
"๋จธ": 196, |
|
"๋จน": 197, |
|
"๋จผ": 198, |
|
"๋ฉ": 199, |
|
"๋ฉ": 200, |
|
"๋ฉฐ": 201, |
|
"๋ฉด": 202, |
|
"๋ช
": 203, |
|
"๋ช": 204, |
|
"๋ชจ": 205, |
|
"๋ชฐ": 206, |
|
"๋ชป": 207, |
|
"๋ฌด": 208, |
|
"๋ฌถ": 209, |
|
"๋ฌธ": 210, |
|
"๋ฌป": 211, |
|
"๋ฌผ": 212, |
|
"๋ญ": 213, |
|
"๋ฏธ": 214, |
|
"๋ฐ": 215, |
|
"๋ฐ": 216, |
|
"๋ฐ": 217, |
|
"๋ฐ": 218, |
|
"๋ฐ": 219, |
|
"๋ฐ": 220, |
|
"๋ฐ": 221, |
|
"๋ฐฉ": 222, |
|
"๋ฐฐ": 223, |
|
"๋ฐฑ": 224, |
|
"๋ฒ": 225, |
|
"๋ฒ": 226, |
|
"๋ฒ": 227, |
|
"๋ฒณ": 228, |
|
"๋ฒผ": 229, |
|
"๋ฒฝ": 230, |
|
"๋ณ": 231, |
|
"๋ณ": 232, |
|
"๋ณด": 233, |
|
"๋ณธ": 234, |
|
"๋ณผ": 235, |
|
"๋ด
": 236, |
|
"๋ด": 237, |
|
"๋ด": 238, |
|
"๋ดค": 239, |
|
"๋ถ": 240, |
|
"๋ถ": 241, |
|
"๋ถ": 242, |
|
"๋ถ": 243, |
|
"๋ธ": 244, |
|
"๋น": 245, |
|
"๋น": 246, |
|
"๋น ": 247, |
|
"๋นจ": 248, |
|
"๋บ": 249, |
|
"๋ฝ": 250, |
|
"๋ฟ": 251, |
|
"๋ฟ": 252, |
|
"์ฌ": 253, |
|
"์ญ": 254, |
|
"์ฐ": 255, |
|
"์ด": 256, |
|
"์ผ": 257, |
|
"์": 258, |
|
"์": 259, |
|
"์": 260, |
|
"์": 261, |
|
"์": 262, |
|
"์ค": 263, |
|
"์": 264, |
|
"์": 265, |
|
"์": 266, |
|
"์ ": 267, |
|
"์ค": 268, |
|
"์ญ": 269, |
|
"์ฏ": 270, |
|
"์ฑ": 271, |
|
"์ธ": 272, |
|
"์
": 273, |
|
"์
จ": 274, |
|
"์": 275, |
|
"์": 276, |
|
"์": 277, |
|
"์ก": 278, |
|
"์": 279, |
|
"์": 280, |
|
"์ ": 281, |
|
"์ฌ": 282, |
|
"์ฝ": 283, |
|
"์ค": 284, |
|
"์จ": 285, |
|
"์ฌ": 286, |
|
"์ต": 287, |
|
"์น": 288, |
|
"์": 289, |
|
"์": 290, |
|
"์ ": 291, |
|
"์ค": 292, |
|
"์ฌ": 293, |
|
"์ญ": 294, |
|
"์ผ": 295, |
|
"์ด": 296, |
|
"์ธ": 297, |
|
"์จ": 298, |
|
"์ฉ": 299, |
|
"์": 300, |
|
"์": 301, |
|
"์": 302, |
|
"์": 303, |
|
"์": 304, |
|
"์": 305, |
|
"์": 306, |
|
"์ ": 307, |
|
"์ก": 308, |
|
"์ค": 309, |
|
"์ผ": 310, |
|
"์ฝ": 311, |
|
"์": 312, |
|
"์": 313, |
|
"์ด": 314, |
|
"์ต": 315, |
|
"์ธ": 316, |
|
"์ป": 317, |
|
"์ผ": 318, |
|
"์": 319, |
|
"์": 320, |
|
"์": 321, |
|
"์": 322, |
|
"์": 323, |
|
"์ฌ": 324, |
|
"์ญ": 325, |
|
"์ฐ": 326, |
|
"์ด": 327, |
|
"์ผ": 328, |
|
"์": 329, |
|
"์": 330, |
|
"์": 331, |
|
"์ค": 332, |
|
"์จ": 333, |
|
"์ฌ": 334, |
|
"์ณ": 335, |
|
"์ท": 336, |
|
"์": 337, |
|
"์": 338, |
|
"์": 339, |
|
"์ธ": 340, |
|
"์": 341, |
|
"์ฉ": 342, |
|
"์ฐ": 343, |
|
"์ด": 344, |
|
"์ธ": 345, |
|
"์": 346, |
|
"์": 347, |
|
"์": 348, |
|
"์": 349, |
|
"์ ": 350, |
|
"์": 351, |
|
"์ ": 352, |
|
"์ก": 353, |
|
"์ต": 354, |
|
"์ผ": 355, |
|
"์": 356, |
|
"์": 357, |
|
"์": 358, |
|
"์": 359, |
|
"์": 360, |
|
"์": 361, |
|
"์ด": 362, |
|
"์ธ": 363, |
|
"์ผ": 364, |
|
"์ฝ": 365, |
|
"์": 366, |
|
"์
": 367, |
|
"์": 368, |
|
"์": 369, |
|
"์": 370, |
|
"์": 371, |
|
"์": 372, |
|
"์": 373, |
|
"์ ": 374, |
|
"์ฅ": 375, |
|
"์ฌ": 376, |
|
"์ ": 377, |
|
"์ ": 378, |
|
"์ ": 379, |
|
"์ ": 380, |
|
"์ ": 381, |
|
"์ ": 382, |
|
"์ ": 383, |
|
"์ ": 384, |
|
"์ ธ": 385, |
|
"์ก": 386, |
|
"์กฐ": 387, |
|
"์กด": 388, |
|
"์ข": 389, |
|
"์ข
": 390, |
|
"์ข": 391, |
|
"์ฃ ": 392, |
|
"์ฃผ": 393, |
|
"์ค": 394, |
|
"์ค": 395, |
|
"์ค": 396, |
|
"์ฆ": 397, |
|
"์ฆ": 398, |
|
"์ฆ": 399, |
|
"์ง": 400, |
|
"์ง": 401, |
|
"์ง": 402, |
|
"์ง": 403, |
|
"์ง": 404, |
|
"์ง": 405, |
|
"์ง": 406, |
|
"์งญ": 407, |
|
"์งฑ": 408, |
|
"์งธ": 409, |
|
"์จ": 410, |
|
"์ชผ": 411, |
|
"์ซ": 412, |
|
"์ฌ": 413, |
|
"์ญ": 414, |
|
"์ฐจ": 415, |
|
"์ฐฌ": 416, |
|
"์ฐฐ": 417, |
|
"์ฐฝ": 418, |
|
"์ฐพ": 419, |
|
"์ฑ
": 420, |
|
"์ฒ": 421, |
|
"์ฒ ": 422, |
|
"์ฒซ": 423, |
|
"์ฒด": 424, |
|
"์ณ": 425, |
|
"์ตธ": 426, |
|
"์ถ": 427, |
|
"์ถ": 428, |
|
"์ถ": 429, |
|
"์ถฉ": 430, |
|
"์ธก": 431, |
|
"์ธต": 432, |
|
"์น": 433, |
|
"์น": 434, |
|
"์น": 435, |
|
"์น ": 436, |
|
"์นญ": 437, |
|
"์บ": 438, |
|
"์ปค": 439, |
|
"์ปต": 440, |
|
"์ปท": 441, |
|
"์ผ": 442, |
|
"์ผ": 443, |
|
"์ผฐ": 444, |
|
"์ฝ": 445, |
|
"ํ": 446, |
|
"ํฌ": 447, |
|
"ํผ": 448, |
|
"ํค": 449, |
|
"ํจ": 450, |
|
"ํฌ": 451, |
|
"ํ": 452, |
|
"ํ": 453, |
|
"ํ": 454, |
|
"ํ": 455, |
|
"ํ": 456, |
|
"ํ": 457, |
|
"ํฐ": 458, |
|
"ํ
": 459, |
|
"ํค": 460, |
|
"ํต": 461, |
|
"ํฌ": 462, |
|
"ํน": 463, |
|
"ํ": 464, |
|
"ํฐ": 465, |
|
"ํ": 466, |
|
"ํ": 467, |
|
"ํ": 468, |
|
"ํฝ": 469, |
|
"ํผ": 470, |
|
"ํด": 471, |
|
"ํธ": 472, |
|
"ํฌ": 473, |
|
"ํ": 474, |
|
"ํ": 475, |
|
"ํ": 476, |
|
"ํ": 477, |
|
"ํผ": 478, |
|
"ํ": 479, |
|
"ํ": 480, |
|
"ํ": 481, |
|
"ํ": 482, |
|
"ํ ": 483, |
|
"ํจ": 484, |
|
"ํฉ": 485, |
|
"ํญ": 486, |
|
"ํด": 487, |
|
"ํ": 488, |
|
"ํ": 489, |
|
"ํฅ": 490, |
|
"ํ": 491, |
|
"ํ": 492, |
|
"ํ": 493, |
|
"ํ": 494, |
|
"ํ": 495, |
|
"ํ": 496, |
|
"ํฉ": 497, |
|
"ํ": 498, |
|
"ํ": 499, |
|
"ํ": 500, |
|
"ํ": 501, |
|
"ํก": 502, |
|
"ํ": 503, |
|
"ํ": 504, |
|
"ํ": 505 |
|
} |
|
|