tamasheq-99-1 / vocab.json
ad019el's picture
Upload tokenizer
ff8bea6
raw history blame
No virus
514 Bytes
{
"[PAD]": 42,
"[UNK]": 41,
"|": 8,
"ء": 23,
"آ": 34,
"أ": 38,
"ؤ": 10,
"إ": 1,
"ئ": 9,
"ا": 4,
"ب": 32,
"ة": 20,
"ت": 21,
"ث": 19,
"ج": 13,
"ح": 37,
"خ": 17,
"د": 26,
"ذ": 27,
"ر": 2,
"ز": 29,
"س": 28,
"ش": 0,
"ص": 24,
"ض": 33,
"ط": 18,
"ظ": 25,
"ع": 7,
"غ": 22,
"ف": 15,
"ق": 3,
"ك": 6,
"ل": 30,
"م": 36,
"ن": 40,
"ه": 11,
"و": 35,
"ى": 31,
"ي": 12,
"ٱ": 39,
"ڤ": 14,
"ک": 5,
"ی": 16
}