tamasheq-99-2 / vocab.json
ad019el's picture
Upload tokenizer
316e0e3
raw
history blame
No virus
526 Bytes
{
"[PAD]": 43,
"[UNK]": 42,
"|": 19,
"ء": 21,
"آ": 18,
"أ": 16,
"ؤ": 23,
"إ": 28,
"ئ": 26,
"ا": 20,
"ب": 10,
"ة": 40,
"ت": 5,
"ث": 32,
"ج": 12,
"ح": 14,
"خ": 17,
"د": 0,
"ذ": 25,
"ر": 37,
"ز": 30,
"س": 4,
"ش": 36,
"ص": 2,
"ض": 3,
"ط": 39,
"ظ": 24,
"ع": 1,
"غ": 9,
"ف": 33,
"ق": 7,
"ك": 35,
"ل": 34,
"م": 8,
"ن": 13,
"ه": 11,
"و": 6,
"ى": 31,
"ي": 38,
"ٱ": 41,
"چ": 22,
"ڤ": 15,
"ک": 27,
"ی": 29
}