tamasheq-99-2 / vocab.json
ad019el's picture
Upload tokenizer
2cbfb85
raw
history blame
No virus
526 Bytes
{
"[PAD]": 43,
"[UNK]": 42,
"|": 34,
"ء": 16,
"آ": 29,
"أ": 11,
"ؤ": 5,
"إ": 38,
"ئ": 8,
"ا": 3,
"ب": 25,
"ة": 6,
"ت": 28,
"ث": 7,
"ج": 24,
"ح": 0,
"خ": 15,
"د": 32,
"ذ": 40,
"ر": 17,
"ز": 33,
"س": 26,
"ش": 19,
"ص": 22,
"ض": 35,
"ط": 36,
"ظ": 23,
"ع": 30,
"غ": 27,
"ف": 41,
"ق": 20,
"ك": 2,
"ل": 12,
"م": 21,
"ن": 37,
"ه": 9,
"و": 1,
"ى": 18,
"ي": 14,
"ٱ": 13,
"چ": 39,
"ڤ": 10,
"ک": 31,
"ی": 4
}