xlsr_ur_training / vocab.json
hadiqa123's picture
add tokenizer
30d6e3e
raw
history blame
694 Bytes
{
"[PAD]": 57,
"[UNK]": 56,
"|": 0,
"،": 1,
"؟": 2,
"ء": 3,
"آ": 4,
"ؤ": 5,
"ئ": 6,
"ا": 7,
"ب": 8,
"ت": 9,
"ث": 10,
"ج": 11,
"ح": 12,
"خ": 13,
"د": 14,
"ذ": 15,
"ر": 16,
"ز": 17,
"س": 18,
"ش": 19,
"ص": 20,
"ض": 21,
"ط": 22,
"ظ": 23,
"ع": 24,
"غ": 25,
"ف": 26,
"ق": 27,
"ل": 28,
"م": 29,
"ن": 30,
"و": 31,
"ى": 32,
"ي": 33,
"ً": 34,
"ُ": 35,
"ِ": 36,
"ّ": 37,
"ٓ": 38,
"ٔ": 39,
"ٰ": 40,
"ٹ": 41,
"پ": 42,
"چ": 43,
"ڈ": 44,
"ڑ": 45,
"ژ": 46,
"ک": 47,
"گ": 48,
"ں": 49,
"ھ": 50,
"ہ": 51,
"ۂ": 52,
"ی": 53,
"ے": 54,
"۔": 55
}