wav / vocab.json
Zienab's picture
Upload tokenizer
8e5641b
raw
history blame contribute delete
No virus
550 Bytes
{
"[PAD]": 45,
"[UNK]": 44,
"|": 0,
"ء": 1,
"آ": 2,
"أ": 3,
"إ": 4,
"ئ": 5,
"ا": 6,
"ب": 7,
"ة": 8,
"ت": 9,
"ث": 10,
"ج": 11,
"ح": 12,
"خ": 13,
"د": 14,
"ذ": 15,
"ر": 16,
"ز": 17,
"س": 18,
"ش": 19,
"ص": 20,
"ض": 21,
"ط": 22,
"ظ": 23,
"ع": 24,
"غ": 25,
"ف": 26,
"ق": 27,
"ك": 28,
"ل": 29,
"م": 30,
"ن": 31,
"ه": 32,
"و": 33,
"ى": 34,
"ي": 35,
"ً": 36,
"ٌ": 37,
"ٍ": 38,
"َ": 39,
"ُ": 40,
"ِ": 41,
"ّ": 42,
"ْ": 43
}