UrduAudio2Text / vocab.json
Umer4's picture
add tokenizer
2194f7f
raw
history blame contribute delete
596 Bytes
{"،": 1, "؟": 2, "ء": 3, "آ": 4, "ؤ": 5, "ئ": 6, "ا": 7, "ب": 8, "ت": 9, "ث": 10, "ج": 11, "ح": 12, "خ": 13, "د": 14, "ذ": 15, "ر": 16, "ز": 17, "س": 18, "ش": 19, "ص": 20, "ض": 21, "ط": 22, "ظ": 23, "ع": 24, "غ": 25, "ف": 26, "ق": 27, "ل": 28, "م": 29, "ن": 30, "و": 31, "ى": 32, "ي": 33, "ً": 34, "َ": 35, "ُ": 36, "ِ": 37, "ّ": 38, "ٓ": 39, "ٔ": 40, "ٰ": 41, "ٹ": 42, "پ": 43, "چ": 44, "ڈ": 45, "ڑ": 46, "ژ": 47, "ک": 48, "گ": 49, "ں": 50, "ھ": 51, "ہ": 52, "ۂ": 53, "ی": 54, "ے": 55, "۔": 56, "’": 57, "|": 0, "[UNK]": 58, "[PAD]": 59}