w2v-bert-odia_v1 / vocab.json
cdactvm's picture
Upload tokenizer
56df9e4 verified
raw
history blame
1.09 kB
{
"0": 1,
"1": 2,
"2": 3,
"4": 4,
"9": 5,
"[PAD]": 84,
"[UNK]": 83,
"|": 0,
"।": 6,
"ଁ": 7,
"ଂ": 8,
"ଃ": 9,
"ଅ": 10,
"ଆ": 11,
"ଇ": 12,
"ଈ": 13,
"ଉ": 14,
"ଊ": 15,
"ଋ": 16,
"ଏ": 17,
"ଐ": 18,
"ଓ": 19,
"ଔ": 20,
"କ": 21,
"ଖ": 22,
"ଗ": 23,
"ଘ": 24,
"ଙ": 25,
"ଚ": 26,
"ଛ": 27,
"ଜ": 28,
"ଝ": 29,
"ଞ": 30,
"ଟ": 31,
"ଠ": 32,
"ଡ": 33,
"ଢ": 34,
"ଣ": 35,
"ତ": 36,
"ଥ": 37,
"ଦ": 38,
"ଧ": 39,
"ନ": 40,
"ପ": 41,
"ଫ": 42,
"ବ": 43,
"ଭ": 44,
"ମ": 45,
"ଯ": 46,
"ର": 47,
"ଲ": 48,
"ଳ": 49,
"ଵ": 50,
"ଶ": 51,
"ଷ": 52,
"ସ": 53,
"ହ": 54,
"଼": 55,
"ା": 56,
"ି": 57,
"ୀ": 58,
"ୁ": 59,
"ୂ": 60,
"ୃ": 61,
"େ": 62,
"ୈ": 63,
"ୋ": 64,
"ୌ": 65,
"୍": 66,
"ଡ଼": 67,
"ଢ଼": 68,
"ୟ": 69,
"୦": 70,
"୧": 71,
"୨": 72,
"୩": 73,
"୪": 74,
"୫": 75,
"୬": 76,
"୭": 77,
"୮": 78,
"୯": 79,
"ୱ": 80,
"‌": 81,
"–": 82
}