mms-tts-ara / vocab.json
sanchit-gandhi's picture
Upload tokenizer
fe4d0d4
raw
history blame
460 Bytes
{
" ": 25,
"_": 37,
"ء": 26,
"آ": 27,
"أ": 20,
"ؤ": 35,
"إ": 4,
"ئ": 38,
"ا": 0,
"ب": 28,
"ة": 7,
"ت": 12,
"ث": 19,
"ج": 13,
"ح": 23,
"خ": 11,
"د": 16,
"ذ": 6,
"ر": 9,
"ز": 34,
"س": 8,
"ش": 32,
"ص": 18,
"ض": 22,
"ط": 10,
"ظ": 14,
"ع": 3,
"غ": 5,
"ف": 36,
"ق": 33,
"ك": 2,
"ل": 31,
"م": 30,
"ن": 1,
"ه": 24,
"و": 29,
"ى": 21,
"ي": 15,
"–": 17
}