URDU-ASR / vocab.json
Shehryar718's picture
Upload tokenizer
61a74e6
raw
history blame contribute delete
No virus
1.04 kB
{
"'": 21,
"[PAD]": 85,
"[UNK]": 84,
"`": 19,
"|": 56,
"،": 15,
"ؑ": 25,
"ؓ": 61,
"ؔ": 66,
"؛": 54,
"؟": 27,
"ء": 82,
"آ": 45,
"أ": 77,
"ؤ": 68,
"ئ": 58,
"ا": 35,
"ب": 80,
"ت": 23,
"ث": 20,
"ج": 44,
"ح": 24,
"خ": 73,
"د": 60,
"ذ": 8,
"ر": 26,
"ز": 18,
"س": 3,
"ش": 13,
"ص": 48,
"ض": 75,
"ط": 31,
"ظ": 65,
"ع": 67,
"غ": 4,
"ف": 52,
"ق": 78,
"ك": 1,
"ل": 41,
"م": 28,
"ن": 29,
"ه": 64,
"و": 53,
"ى": 16,
"ي": 81,
"ً": 51,
"َ": 83,
"ُ": 57,
"ِ": 14,
"ّ": 30,
"ْ": 79,
"ٓ": 33,
"ٔ": 71,
"ٗ": 43,
"ٰ": 7,
"ٹ": 42,
"پ": 76,
"چ": 17,
"ڈ": 38,
"ڑ": 12,
"ژ": 72,
"ک": 74,
"گ": 62,
"ں": 10,
"ھ": 2,
"ہ": 40,
"ۂ": 34,
"ۃ": 5,
"ی": 9,
"ے": 0,
"ۓ": 46,
"۔": 69,
"’": 22,
"…": 47,
"ﭨ": 50,
"ﮭ": 70,
"ﮯ": 63,
"ﯾ": 59,
"ﷲ": 11,
"ﷺ": 55,
"ﺗ": 37,
"ﺘ": 6,
"ﺩ": 32,
"ﺲ": 39,
"ﻧ": 36,
"ﻮ": 49
}