w2v-bert-2_7_datasets / vocab.json
Bajiyo's picture
Upload tokenizer
ce60822 verified
raw
history blame
No virus
1.02 kB
{
"[PAD]": 78,
"[UNK]": 77,
"_": 1,
"|": 0,
"ം": 2,
"ഃ": 3,
"അ": 4,
"ആ": 5,
"ഇ": 6,
"ഈ": 7,
"ഉ": 8,
"ഊ": 9,
"ഋ": 10,
"എ": 11,
"ഏ": 12,
"ഐ": 13,
"ഒ": 14,
"ഓ": 15,
"ഔ": 16,
"ക": 17,
"ഖ": 18,
"ഗ": 19,
"ഘ": 20,
"ങ": 21,
"ച": 22,
"ഛ": 23,
"ജ": 24,
"ഝ": 25,
"ഞ": 26,
"ട": 27,
"ഠ": 28,
"ഡ": 29,
"ഢ": 30,
"ണ": 31,
"ത": 32,
"ഥ": 33,
"ദ": 34,
"ധ": 35,
"ന": 36,
"പ": 37,
"ഫ": 38,
"ബ": 39,
"ഭ": 40,
"മ": 41,
"യ": 42,
"ര": 43,
"റ": 44,
"ല": 45,
"ള": 46,
"ഴ": 47,
"വ": 48,
"ശ": 49,
"ഷ": 50,
"സ": 51,
"ഹ": 52,
"ാ": 53,
"ി": 54,
"ീ": 55,
"ു": 56,
"ൂ": 57,
"ൃ": 58,
"െ": 59,
"േ": 60,
"ൈ": 61,
"ൊ": 62,
"ോ": 63,
"ൌ": 64,
"്": 65,
"ൗ": 66,
"൱": 67,
"ൺ": 68,
"ൻ": 69,
"ർ": 70,
"ൽ": 71,
"ൾ": 72,
"ൿ": 73,
"‌": 74,
"‍": 75,
"’": 76
}