URDU-ASR-25-EPOCH / vocab.json
Shehryar718's picture
Upload tokenizer
1226cd9
raw
history blame
No virus
1.04 kB
{
"'": 83,
"[PAD]": 85,
"[UNK]": 84,
"`": 59,
"|": 42,
"،": 29,
"ؑ": 19,
"ؓ": 67,
"ؔ": 1,
"؛": 13,
"؟": 46,
"ء": 6,
"آ": 78,
"أ": 34,
"ؤ": 44,
"ئ": 16,
"ا": 32,
"ب": 23,
"ت": 72,
"ث": 24,
"ج": 74,
"ح": 21,
"خ": 70,
"د": 64,
"ذ": 35,
"ر": 9,
"ز": 45,
"س": 54,
"ش": 15,
"ص": 26,
"ض": 5,
"ط": 43,
"ظ": 49,
"ع": 36,
"غ": 55,
"ف": 8,
"ق": 30,
"ك": 66,
"ل": 57,
"م": 27,
"ن": 61,
"ه": 18,
"و": 47,
"ى": 39,
"ي": 76,
"ً": 17,
"َ": 52,
"ُ": 82,
"ِ": 80,
"ّ": 10,
"ْ": 60,
"ٓ": 14,
"ٔ": 68,
"ٗ": 31,
"ٰ": 65,
"ٹ": 50,
"پ": 3,
"چ": 69,
"ڈ": 41,
"ڑ": 62,
"ژ": 38,
"ک": 75,
"گ": 7,
"ں": 51,
"ھ": 37,
"ہ": 81,
"ۂ": 22,
"ۃ": 4,
"ی": 58,
"ے": 48,
"ۓ": 20,
"۔": 56,
"’": 77,
"…": 33,
"ﭨ": 71,
"ﮭ": 2,
"ﮯ": 11,
"ﯾ": 12,
"ﷲ": 73,
"ﷺ": 40,
"ﺗ": 53,
"ﺘ": 79,
"ﺩ": 63,
"ﺲ": 28,
"ﻧ": 25,
"ﻮ": 0
}