UrduWav2Vec2Large / vocab.json
mwz's picture
Upload tokenizer
1fbb660
raw
history blame contribute delete
No virus
1.04 kB
{
"'": 70,
"[PAD]": 85,
"[UNK]": 84,
"`": 81,
"|": 33,
"،": 65,
"ؑ": 80,
"ؓ": 18,
"ؔ": 38,
"؛": 68,
"؟": 30,
"ء": 26,
"آ": 21,
"أ": 58,
"ؤ": 29,
"ئ": 74,
"ا": 22,
"ب": 11,
"ت": 3,
"ث": 62,
"ج": 0,
"ح": 10,
"خ": 44,
"د": 53,
"ذ": 42,
"ر": 1,
"ز": 64,
"س": 14,
"ش": 7,
"ص": 46,
"ض": 66,
"ط": 51,
"ظ": 17,
"ع": 13,
"غ": 40,
"ف": 56,
"ق": 71,
"ك": 16,
"ل": 2,
"م": 34,
"ن": 24,
"ه": 37,
"و": 69,
"ى": 50,
"ي": 67,
"ً": 75,
"َ": 82,
"ُ": 6,
"ِ": 36,
"ّ": 35,
"ْ": 39,
"ٓ": 20,
"ٔ": 78,
"ٗ": 4,
"ٰ": 43,
"ٹ": 41,
"پ": 57,
"چ": 59,
"ڈ": 45,
"ڑ": 73,
"ژ": 54,
"ک": 83,
"گ": 9,
"ں": 28,
"ھ": 47,
"ہ": 32,
"ۂ": 25,
"ۃ": 76,
"ی": 79,
"ے": 72,
"ۓ": 48,
"۔": 31,
"’": 61,
"…": 55,
"ﭨ": 60,
"ﮭ": 8,
"ﮯ": 63,
"ﯾ": 52,
"ﷲ": 49,
"ﷺ": 15,
"ﺗ": 19,
"ﺘ": 23,
"ﺩ": 5,
"ﺲ": 27,
"ﻧ": 77,
"ﻮ": 12
}