w2v-bert-2.0-ur / vocab.json
mwz's picture
Upload tokenizer
e142e6d verified
raw
history blame
994 Bytes
{
"[PAD]": 81,
"[UNK]": 80,
"`": 1,
"|": 0,
"،": 2,
"ؐ": 3,
"ؑ": 4,
"ؓ": 5,
"ؔ": 6,
"؛": 7,
"؟": 8,
"ء": 9,
"آ": 10,
"أ": 11,
"ؤ": 12,
"ئ": 13,
"ا": 14,
"ب": 15,
"ت": 16,
"ث": 17,
"ج": 18,
"ح": 19,
"خ": 20,
"د": 21,
"ذ": 22,
"ر": 23,
"ز": 24,
"س": 25,
"ش": 26,
"ص": 27,
"ض": 28,
"ط": 29,
"ظ": 30,
"ع": 31,
"غ": 32,
"ف": 33,
"ق": 34,
"ل": 35,
"م": 36,
"ن": 37,
"ه": 38,
"و": 39,
"ي": 40,
"ً": 41,
"َ": 42,
"ُ": 43,
"ِ": 44,
"ّ": 45,
"ٓ": 46,
"ٔ": 47,
"ٰ": 48,
"ٴ": 49,
"ٹ": 50,
"پ": 51,
"چ": 52,
"ڈ": 53,
"ڑ": 54,
"ژ": 55,
"ک": 56,
"گ": 57,
"ں": 58,
"ھ": 59,
"ہ": 60,
"ۂ": 61,
"ۃ": 62,
"ی": 63,
"ے": 64,
"ۓ": 65,
"۔": 66,
"’": 67,
"ﭨ": 68,
"ﮭ": 69,
"ﮯ": 70,
"ﯾ": 71,
"ﷲ": 72,
"ﷺ": 73,
"ﺗ": 74,
"ﺘ": 75,
"ﺩ": 76,
"ﺲ": 77,
"ﻧ": 78,
"ﻮ": 79
}