tamasheq-99-2 / vocab.json
ad019el's picture
Upload tokenizer
41577a2
raw
history blame
No virus
538 Bytes
{
"[PAD]": 44,
"[UNK]": 43,
"|": 0,
"̣": 23,
"ء": 7,
"آ": 11,
"أ": 22,
"ؤ": 42,
"إ": 12,
"ئ": 10,
"ا": 3,
"ب": 24,
"ة": 6,
"ت": 20,
"ث": 14,
"ج": 40,
"ح": 1,
"خ": 8,
"د": 16,
"ذ": 29,
"ر": 21,
"ز": 41,
"س": 31,
"ش": 9,
"ص": 25,
"ض": 5,
"ط": 35,
"ظ": 19,
"ع": 4,
"غ": 33,
"ف": 13,
"ق": 32,
"ك": 30,
"ل": 15,
"م": 38,
"ن": 36,
"ه": 37,
"و": 17,
"ى": 34,
"ي": 26,
"ٱ": 18,
"چ": 28,
"ڤ": 39,
"ک": 27,
"ی": 2
}