xls-r_cv_ur / vocab.json
hadiqa123's picture
add tokenizer
9f0f86b
raw
history blame
536 Bytes
{
" ": 42,
"PAD": 43,
"[UNK]": 44,
"آ": 38,
"أ": 10,
"ؤ": 4,
"ئ": 29,
"ا": 20,
"ب": 28,
"ت": 3,
"ث": 25,
"ج": 31,
"ح": 17,
"خ": 11,
"د": 12,
"ذ": 24,
"ر": 7,
"ز": 15,
"س": 18,
"ش": 30,
"ص": 40,
"ض": 1,
"ط": 37,
"ظ": 13,
"ع": 8,
"غ": 5,
"ف": 27,
"ق": 21,
"ل": 16,
"م": 41,
"ن": 26,
"و": 2,
"ً": 32,
"ٹ": 22,
"پ": 35,
"چ": 14,
"ڈ": 19,
"ڑ": 36,
"ک": 6,
"گ": 23,
"ں": 39,
"ھ": 33,
"ہ": 0,
"ی": 34,
"ے": 9
}