URDU-ASR-25-EPOCH / vocab.json
Shehryar718's picture
Upload tokenizer
ab0f156
{
"'": 28,
"[PAD]": 85,
"[UNK]": 84,
"`": 49,
"|": 19,
"،": 36,
"ؑ": 76,
"ؓ": 45,
"ؔ": 57,
"؛": 7,
"؟": 25,
"ء": 18,
"آ": 59,
"أ": 35,
"ؤ": 12,
"ئ": 72,
"ا": 47,
"ب": 22,
"ت": 34,
"ث": 15,
"ج": 32,
"ح": 33,
"خ": 23,
"د": 82,
"ذ": 68,
"ر": 2,
"ز": 3,
"س": 75,
"ش": 14,
"ص": 30,
"ض": 17,
"ط": 69,
"ظ": 11,
"ع": 41,
"غ": 67,
"ف": 26,
"ق": 66,
"ك": 70,
"ل": 4,
"م": 62,
"ن": 5,
"ه": 16,
"و": 71,
"ى": 55,
"ي": 10,
"ً": 21,
"َ": 80,
"ُ": 64,
"ِ": 73,
"ّ": 53,
"ْ": 31,
"ٓ": 0,
"ٔ": 43,
"ٗ": 77,
"ٰ": 81,
"ٹ": 20,
"پ": 24,
"چ": 83,
"ڈ": 54,
"ڑ": 74,
"ژ": 44,
"ک": 78,
"گ": 29,
"ں": 1,
"ھ": 60,
"ہ": 61,
"ۂ": 27,
"ۃ": 9,
"ی": 50,
"ے": 38,
"ۓ": 48,
"۔": 52,
"’": 79,
"…": 51,
"ﭨ": 40,
"ﮭ": 42,
"ﮯ": 37,
"ﯾ": 6,
"ﷲ": 58,
"ﷺ": 65,
"ﺗ": 8,
"ﺘ": 46,
"ﺩ": 39,
"ﺲ": 63,
"ﻧ": 56,
"ﻮ": 13
}