xls-r_cv_ur / vocab.json
hadiqa123's picture
add tokenizer
e9b3156
raw
history blame
536 Bytes
{
" ": 20,
"PAD": 43,
"[UNK]": 44,
"آ": 1,
"أ": 0,
"ؤ": 18,
"ئ": 29,
"ا": 13,
"ب": 33,
"ت": 25,
"ث": 15,
"ج": 37,
"ح": 17,
"خ": 31,
"د": 12,
"ذ": 24,
"ر": 42,
"ز": 39,
"س": 41,
"ش": 27,
"ص": 21,
"ض": 9,
"ط": 14,
"ظ": 26,
"ع": 35,
"غ": 30,
"ف": 19,
"ق": 34,
"ل": 32,
"م": 16,
"ن": 28,
"و": 40,
"ً": 6,
"ٹ": 5,
"پ": 23,
"چ": 10,
"ڈ": 7,
"ڑ": 4,
"ک": 8,
"گ": 11,
"ں": 36,
"ھ": 3,
"ہ": 2,
"ی": 38,
"ے": 22
}