xls-r_cv_ur / vocab.json
hadiqa123's picture
add tokenizer
75a57e4
raw
history blame
202 Bytes
{
" ": 6,
"[PAD]": 16,
"[UNK]": 15,
"ا": 7,
"ب": 0,
"ت": 11,
"د": 4,
"ز": 3,
"س": 5,
"ل": 2,
"م": 14,
"ڑ": 8,
"ک": 13,
"ھ": 10,
"ہ": 12,
"ی": 9,
"ے": 1
}