xls-r_cv_ur / vocab.json
hadiqa123's picture
add tokenizer
93d2dc3
raw
history blame
536 Bytes
{
" ": 33,
"PAD": 43,
"[UNK]": 44,
"آ": 1,
"أ": 42,
"ؤ": 21,
"ئ": 28,
"ا": 9,
"ب": 34,
"ت": 22,
"ث": 37,
"ج": 30,
"ح": 35,
"خ": 19,
"د": 7,
"ذ": 29,
"ر": 0,
"ز": 18,
"س": 39,
"ش": 20,
"ص": 13,
"ض": 26,
"ط": 11,
"ظ": 40,
"ع": 23,
"غ": 8,
"ف": 5,
"ق": 6,
"ل": 12,
"م": 3,
"ن": 27,
"و": 41,
"ً": 14,
"ٹ": 17,
"پ": 25,
"چ": 24,
"ڈ": 32,
"ڑ": 10,
"ک": 36,
"گ": 16,
"ں": 15,
"ھ": 38,
"ہ": 2,
"ی": 31,
"ے": 4
}