tamasheq-99-6 / vocab.json
ad019el's picture
Upload tokenizer
a3c57b5
raw
history blame
No virus
514 Bytes
{
"[PAD]": 42,
"[UNK]": 41,
"|": 34,
"ء": 11,
"آ": 38,
"أ": 26,
"ؤ": 13,
"إ": 20,
"ئ": 39,
"ا": 19,
"ب": 3,
"ة": 17,
"ت": 32,
"ث": 8,
"ج": 27,
"ح": 21,
"خ": 0,
"د": 9,
"ذ": 37,
"ر": 16,
"ز": 1,
"س": 14,
"ش": 36,
"ص": 40,
"ض": 12,
"ط": 22,
"ظ": 28,
"ع": 30,
"غ": 6,
"ف": 33,
"ق": 31,
"ك": 24,
"ل": 10,
"م": 5,
"ن": 35,
"ه": 15,
"و": 7,
"ى": 25,
"ي": 2,
"ٱ": 4,
"ڤ": 18,
"ک": 29,
"ی": 23
}