w2v2-bert-urdu / vocab.json
UmarRamzan's picture
Upload tokenizer
7483787 verified
raw
history blame
562 Bytes
{
"[PAD]": 46,
"[UNK]": 45,
"|": 0,
"أ": 1,
"ؤ": 2,
"ئ": 3,
"ا": 4,
"ب": 5,
"ت": 6,
"ث": 7,
"ج": 8,
"ح": 9,
"خ": 10,
"د": 11,
"ذ": 12,
"ر": 13,
"ز": 14,
"س": 15,
"ش": 16,
"ص": 17,
"ض": 18,
"ط": 19,
"ظ": 20,
"ع": 21,
"غ": 22,
"ف": 23,
"ق": 24,
"ل": 25,
"م": 26,
"ن": 27,
"و": 28,
"ٹ": 29,
"پ": 30,
"چ": 31,
"ڈ": 32,
"ڑ": 33,
"ژ": 34,
"ک": 35,
"گ": 36,
"ں": 37,
"ھ": 38,
"ہ": 39,
"ۂ": 40,
"ۃ": 41,
"ی": 42,
"ے": 43,
"ۓ": 44
}