wav2vec2-mal / vocab.json
manjugeorge's picture
Upload tokenizer
e41638a verified
raw
history blame
1.08 kB
{
"\n": 66,
"0": 77,
"1": 39,
"2": 28,
"3": 15,
"4": 4,
"5": 33,
"7": 11,
"9": 14,
"[PAD]": 84,
"[UNK]": 83,
"o": 73,
"|": 69,
"ം": 75,
"അ": 5,
"ആ": 42,
"ഇ": 74,
"ഈ": 27,
"ഉ": 23,
"ഊ": 50,
"എ": 70,
"ഏ": 81,
"ഐ": 31,
"ഒ": 37,
"ഓ": 52,
"ഔ": 2,
"ക": 3,
"ഖ": 9,
"ഗ": 32,
"ഘ": 57,
"ങ": 61,
"ച": 36,
"ഛ": 18,
"ജ": 59,
"ഞ": 82,
"ട": 78,
"ഠ": 44,
"ഡ": 48,
"ഢ": 38,
"ണ": 49,
"ത": 41,
"ഥ": 8,
"ദ": 17,
"ധ": 79,
"ന": 65,
"പ": 51,
"ഫ": 55,
"ബ": 56,
"ഭ": 60,
"മ": 22,
"യ": 63,
"ര": 35,
"റ": 12,
"ല": 20,
"ള": 19,
"ഴ": 68,
"വ": 0,
"ശ": 30,
"ഷ": 13,
"സ": 45,
"ഹ": 25,
"ാ": 46,
"ി": 54,
"ീ": 64,
"ു": 26,
"ൂ": 10,
"ൃ": 53,
"െ": 29,
"േ": 58,
"ൈ": 21,
"ൊ": 72,
"ോ": 7,
"ൌ": 6,
"്": 1,
"ൗ": 76,
"ൺ": 62,
"ൻ": 16,
"ർ": 43,
"ൽ": 34,
"ൾ": 47,
"‌": 24,
"‍": 80,
"“": 71,
"”": 40,
"": 67
}