wav2vec2-Malayalam / vocab.json
Bluecast's picture
Upload tokenizer
b411059 verified
raw
history blame
955 Bytes
{
"'": 62,
"[PAD]": 73,
"[UNK]": 72,
"|": 70,
"ം": 64,
"ഃ": 15,
"അ": 61,
"ആ": 31,
"ഇ": 42,
"ഈ": 9,
"ഉ": 68,
"ഊ": 7,
"എ": 41,
"ഏ": 63,
"ഐ": 26,
"ഒ": 17,
"ഓ": 46,
"ഔ": 47,
"ക": 53,
"ഖ": 36,
"ഗ": 13,
"ഘ": 2,
"ങ": 22,
"ച": 25,
"ഛ": 0,
"ജ": 71,
"ഞ": 39,
"ട": 3,
"ഠ": 55,
"ഡ": 6,
"ഢ": 45,
"ണ": 57,
"ത": 16,
"ഥ": 20,
"ദ": 59,
"ധ": 43,
"ന": 44,
"പ": 66,
"ഫ": 5,
"ബ": 27,
"ഭ": 4,
"മ": 11,
"യ": 38,
"ര": 56,
"റ": 18,
"ല": 37,
"ള": 33,
"ഴ": 14,
"വ": 40,
"ശ": 8,
"ഷ": 1,
"സ": 54,
"ഹ": 19,
"ാ": 65,
"ി": 12,
"ീ": 58,
"ു": 30,
"ൂ": 49,
"ൃ": 69,
"െ": 67,
"േ": 51,
"ൈ": 32,
"ൊ": 24,
"ോ": 10,
"ൌ": 23,
"്": 29,
"ൗ": 28,
"ൺ": 34,
"ൻ": 21,
"ർ": 60,
"ൽ": 50,
"ൾ": 35,
"ൿ": 48,
"’": 52
}