tamasheq-98-2 / vocab.json
ad019el's picture
add tokenizer
a478c86
raw
history blame
No virus
746 Bytes
{
"/": 31,
"0": 3,
"1": 39,
"2": 55,
"7": 15,
"9": 21,
"[PAD]": 63,
"[UNK]": 62,
"_": 47,
"a": 29,
"c": 34,
"e": 53,
"f": 11,
"j": 6,
"l": 58,
"m": 50,
"o": 5,
"q": 46,
"r": 45,
"t": 17,
"u": 23,
"w": 7,
"|": 25,
"ء": 8,
"آ": 44,
"أ": 22,
"ؤ": 40,
"إ": 36,
"ئ": 41,
"ا": 24,
"ب": 16,
"ة": 12,
"ت": 30,
"ث": 2,
"ج": 56,
"ح": 37,
"خ": 43,
"د": 26,
"ذ": 33,
"ر": 32,
"ز": 35,
"س": 42,
"ش": 59,
"ص": 54,
"ض": 4,
"ط": 13,
"ظ": 49,
"ع": 19,
"غ": 61,
"ف": 27,
"ق": 20,
"ك": 52,
"ل": 9,
"م": 14,
"ن": 38,
"ه": 0,
"و": 57,
"ى": 48,
"ي": 28,
"ٱ": 1,
"چ": 60,
"ڤ": 18,
"ک": 10,
"ی": 51
}