apac_5sents_XLS-R / vocab.json
slplab's picture
Upload tokenizer
99cc8d9
{
"[PAD]": 116,
"[UNK]": 115,
"|": 0,
"๊ฐ€": 1,
"๊ฐ‘": 2,
"๊ฑฐ": 3,
"๊ฒฝ": 4,
"๊ณ ": 5,
"๊ตญ": 6,
"๊ตด": 7,
"๊ทธ": 8,
"๊ธฐ": 9,
"๊ป˜": 10,
"๊ฝƒ": 11,
"๋ผ": 12,
"๋‚˜": 13,
"๋‚ฌ": 14,
"๋„ค": 15,
"๋ˆˆ": 16,
"๋Š”": 17,
"๋Š˜": 18,
"๋‹ˆ": 19,
"๋‹ค": 20,
"๋‹จ": 21,
"๋Œ€": 22,
"๋”": 23,
"๋„": 24,
"๋™": 25,
"๋“ ": 26,
"๋”ธ": 27,
"๋ผ": 28,
"๋žŒ": 29,
"๋ž‘": 30,
"๋ž˜": 31,
"๋ฆฌ": 32,
"๋งˆ": 33,
"๋งŒ": 34,
"๋ง": 35,
"๋จธ": 36,
"๋ชจ": 37,
"๋ฌด": 38,
"๋ฌผ": 39,
"๋ฏธ": 40,
"๋ฐ”": 41,
"๋ฑ€": 42,
"๋ฒ„": 43,
"๋ณ‘": 44,
"๋ณด": 45,
"๋ถ": 46,
"๋น„": 47,
"๋น—": 48,
"๋น ": 49,
"๋นจ": 50,
"์‚ฌ": 51,
"์‚ฐ": 52,
"์ƒ‰": 53,
"์ƒ": 54,
"์„œ": 55,
"์„": 56,
"์„ธ": 57,
"์†Œ": 58,
"์†ก": 59,
"์ˆ˜": 60,
"์‹œ": 61,
"์‹ค": 62,
"์‹ถ": 63,
"์‹ธ": 64,
"์Ÿ": 65,
"์•„": 66,
"์•ˆ": 67,
"์–‘": 68,
"์–ด": 69,
"์–ผ": 70,
"์—„": 71,
"์—†": 72,
"์—": 73,
"์˜ค": 74,
"์˜ฅ": 75,
"์˜จ": 76,
"์˜ฌ": 77,
"์š”": 78,
"์šฐ": 79,
"์›Œ": 80,
"์›": 81,
"์„": 82,
"์ด": 83,
"์žˆ": 84,
"์ž": 85,
"์ž”": 86,
"์žฅ": 87,
"์ œ": 88,
"์กŒ": 89,
"์กฑ": 90,
"์ข…": 91,
"์ฃผ": 92,
"์ง€": 93,
"์ฐข": 94,
"์ฑ…": 95,
"์ถ”": 96,
"์นจ": 97,
"์ปด": 98,
"์ปต": 99,
"ํ€ด": 100,
"ํƒ•": 101,
"ํ…Œ": 102,
"ํ† ": 103,
"ํŒŒ": 104,
"ํŽธ": 105,
"ํฌ": 106,
"ํ•˜": 107,
"ํ•œ": 108,
"ํ•จ": 109,
"ํ•ด": 110,
"ํ–„": 111,
"ํ˜ธ": 112,
"ํ˜ผ": 113,
"ํ™”": 114
}