hassnain's picture
add tokenizer
16ca6de
raw
history blame
516 Bytes
{"ث": 0, "و": 1, "ج": 2, "ش": 3, "م": 4, "ع": 5, "َ": 6, "ڑ": 7, "ُ": 8, "ا": 9, "ٹ": 10, "‌": 11, "س": 12, "ص": 13, "ّ": 14, "ن": 15, "غ": 16, "ک": 17, "ر": 18, "ی": 19, "ح": 20, "ئ": 22, "ل": 23, "ڈ": 24, "ٔ": 25, "ز": 26, "ط": 27, "ذ": 28, "خ": 29, "ق": 30, "ف": 31, "آ": 32, "ؤ": 33, "د": 34, "پ": 35, "ھ": 36, "ِ": 37, "ہ": 38, "ژ": 39, "ً": 40, "ں": 41, "ض": 42, "گ": 43, "ء": 44, "ظ": 45, "چ": 46, "ے": 47, "ت": 48, "ب": 49, "|": 21, "[UNK]": 50, "[PAD]": 51}