xls-r_cv_ur / vocab.json
hadiqa123's picture
add tokenizer
ac7958c
raw
history blame
536 Bytes
{
" ": 35,
"PAD": 43,
"[UNK]": 44,
"آ": 7,
"أ": 2,
"ؤ": 27,
"ئ": 15,
"ا": 26,
"ب": 39,
"ت": 32,
"ث": 31,
"ج": 11,
"ح": 29,
"خ": 37,
"د": 23,
"ذ": 21,
"ر": 34,
"ز": 20,
"س": 18,
"ش": 33,
"ص": 42,
"ض": 5,
"ط": 9,
"ظ": 8,
"ع": 24,
"غ": 28,
"ف": 0,
"ق": 22,
"ل": 19,
"م": 4,
"ن": 3,
"و": 14,
"ً": 13,
"ٹ": 38,
"پ": 36,
"چ": 6,
"ڈ": 17,
"ڑ": 40,
"ک": 16,
"گ": 12,
"ں": 30,
"ھ": 25,
"ہ": 10,
"ی": 1,
"ے": 41
}