w2v-bert-kannada_new / vocab.json
cdactvm's picture
Upload tokenizer
4681f8f verified
{
"/": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"7": 9,
"8": 10,
"9": 11,
"I": 12,
"U": 13,
"[PAD]": 90,
"[UNK]": 89,
"_": 14,
"|": 0,
"ಂ": 15,
"ಃ": 16,
"ಅ": 17,
"ಆ": 18,
"ಇ": 19,
"ಈ": 20,
"ಉ": 21,
"ಊ": 22,
"ಋ": 23,
"ಎ": 24,
"ಏ": 25,
"ಐ": 26,
"ಒ": 27,
"ಓ": 28,
"ಔ": 29,
"ಕ": 30,
"ಖ": 31,
"ಗ": 32,
"ಘ": 33,
"ಙ": 34,
"ಚ": 35,
"ಛ": 36,
"ಜ": 37,
"ಝ": 38,
"ಞ": 39,
"ಟ": 40,
"ಠ": 41,
"ಡ": 42,
"ಢ": 43,
"ಣ": 44,
"ತ": 45,
"ಥ": 46,
"ದ": 47,
"ಧ": 48,
"ನ": 49,
"ಪ": 50,
"ಫ": 51,
"ಬ": 52,
"ಭ": 53,
"ಮ": 54,
"ಯ": 55,
"ರ": 56,
"ಱ": 57,
"ಲ": 58,
"ಳ": 59,
"ವ": 60,
"ಶ": 61,
"ಷ": 62,
"ಸ": 63,
"ಹ": 64,
"ಾ": 65,
"ಿ": 66,
"ೀ": 67,
"ು": 68,
"ೂ": 69,
"ೃ": 70,
"ೆ": 71,
"ೇ": 72,
"ೈ": 73,
"ೊ": 74,
"ೋ": 75,
"ೌ": 76,
"್": 77,
"ೕ": 78,
"ೖ": 79,
"೦": 80,
"೧": 81,
"೨": 82,
"೩": 83,
"೪": 84,
"೫": 85,
"೮": 86,
"​": 87,
"‍": 88
}