w2v-bert-odia_v1 / vocab.json
cdactvm's picture
Upload tokenizer
fe96efd verified
raw
history blame
1.22 kB
{
"\"": 1,
"-": 2,
".": 3,
"0": 4,
"1": 5,
"2": 6,
"4": 7,
"5": 8,
"7": 9,
"8": 10,
"9": 11,
":": 12,
";": 13,
"[PAD]": 95,
"[UNK]": 94,
"|": 0,
"।": 14,
"ଁ": 15,
"ଂ": 16,
"ଃ": 17,
"ଅ": 18,
"ଆ": 19,
"ଇ": 20,
"ଈ": 21,
"ଉ": 22,
"ଊ": 23,
"ଋ": 24,
"ଏ": 25,
"ଐ": 26,
"ଓ": 27,
"ଔ": 28,
"କ": 29,
"ଖ": 30,
"ଗ": 31,
"ଘ": 32,
"ଙ": 33,
"ଚ": 34,
"ଛ": 35,
"ଜ": 36,
"ଝ": 37,
"ଞ": 38,
"ଟ": 39,
"ଠ": 40,
"ଡ": 41,
"ଢ": 42,
"ଣ": 43,
"ତ": 44,
"ଥ": 45,
"ଦ": 46,
"ଧ": 47,
"ନ": 48,
"ପ": 49,
"ଫ": 50,
"ବ": 51,
"ଭ": 52,
"ମ": 53,
"ଯ": 54,
"ର": 55,
"ଲ": 56,
"ଳ": 57,
"ଵ": 58,
"ଶ": 59,
"ଷ": 60,
"ସ": 61,
"ହ": 62,
"଼": 63,
"ା": 64,
"ି": 65,
"ୀ": 66,
"ୁ": 67,
"ୂ": 68,
"ୃ": 69,
"େ": 70,
"ୈ": 71,
"ୋ": 72,
"ୌ": 73,
"୍": 74,
"ଡ଼": 75,
"ଢ଼": 76,
"ୟ": 77,
"୦": 78,
"୧": 79,
"୨": 80,
"୩": 81,
"୪": 82,
"୫": 83,
"୬": 84,
"୭": 85,
"୮": 86,
"୯": 87,
"ୱ": 88,
"‌": 89,
"–": 90,
"‘": 91,
"“": 92,
"”": 93
}