tamasheq-99-2 / vocab.json
ad019el's picture
Upload tokenizer
506a1cf
raw
history blame
No virus
526 Bytes
{
"[PAD]": 43,
"[UNK]": 42,
"|": 35,
"ء": 30,
"آ": 39,
"أ": 41,
"ؤ": 2,
"إ": 32,
"ئ": 24,
"ا": 5,
"ب": 0,
"ة": 18,
"ت": 9,
"ث": 11,
"ج": 8,
"ح": 22,
"خ": 37,
"د": 16,
"ذ": 4,
"ر": 19,
"ز": 29,
"س": 26,
"ش": 12,
"ص": 27,
"ض": 6,
"ط": 34,
"ظ": 33,
"ع": 21,
"غ": 17,
"ف": 25,
"ق": 23,
"ك": 7,
"ل": 14,
"م": 31,
"ن": 3,
"ه": 15,
"و": 40,
"ى": 13,
"ي": 20,
"ٱ": 10,
"چ": 38,
"ڤ": 1,
"ک": 28,
"ی": 36
}