Thunpitcha's picture
Upload tokenizer
c84e3e4
raw
history blame
1.1 kB
{
"'": 41,
"[PAD]": 87,
"[UNK]": 86,
"_": 30,
"a": 4,
"c": 39,
"e": 5,
"h": 80,
"i": 40,
"j": 61,
"k": 81,
"l": 63,
"m": 16,
"n": 70,
"o": 44,
"r": 31,
"s": 11,
"t": 45,
"y": 21,
"|": 29,
"~": 23,
"ก": 3,
"ข": 58,
"ค": 36,
"ฆ": 12,
"ง": 37,
"จ": 38,
"ฉ": 75,
"ช": 35,
"ซ": 8,
"ฌ": 74,
"ญ": 73,
"ฎ": 13,
"ฏ": 48,
"ฐ": 85,
"ฑ": 60,
"ฒ": 82,
"ณ": 34,
"ด": 57,
"ต": 28,
"ถ": 72,
"ท": 51,
"ธ": 76,
"น": 6,
"บ": 42,
"ป": 78,
"ผ": 46,
"ฝ": 69,
"พ": 1,
"ฟ": 67,
"ภ": 68,
"ม": 77,
"ย": 26,
"ร": 79,
"ฤ": 71,
"ล": 65,
"ว": 54,
"ศ": 2,
"ษ": 64,
"ส": 56,
"ห": 20,
"ฬ": 55,
"อ": 15,
"ฮ": 49,
"ะ": 83,
"ั": 47,
"า": 10,
"ำ": 19,
"ิ": 27,
"ี": 0,
"ึ": 33,
"ื": 53,
"ุ": 43,
"ู": 52,
"เ": 17,
"แ": 32,
"โ": 9,
"ใ": 59,
"ไ": 18,
"ๅ": 66,
"ๆ": 14,
"็": 62,
"่": 50,
"้": 22,
"๊": 7,
"๋": 25,
"์": 84,
"’": 24
}