Upload tokenizer
fbe01dd
verified
|
{ |
|
"ardz": { |
|
"[PAD]": 55, |
|
"[UNK]": 54, |
|
"e": 1, |
|
"h": 2, |
|
"i": 3, |
|
"k": 4, |
|
"n": 5, |
|
"o": 6, |
|
"s": 7, |
|
"u": 8, |
|
"|": 0, |
|
"ء": 9, |
|
"آ": 10, |
|
"أ": 11, |
|
"ؤ": 12, |
|
"إ": 13, |
|
"ئ": 14, |
|
"ا": 15, |
|
"ب": 16, |
|
"ة": 17, |
|
"ت": 18, |
|
"ث": 19, |
|
"ج": 20, |
|
"ح": 21, |
|
"خ": 22, |
|
"د": 23, |
|
"ذ": 24, |
|
"ر": 25, |
|
"ز": 26, |
|
"س": 27, |
|
"ش": 28, |
|
"ص": 29, |
|
"ض": 30, |
|
"ط": 31, |
|
"ظ": 32, |
|
"ع": 33, |
|
"غ": 34, |
|
"ـ": 35, |
|
"ف": 36, |
|
"ق": 37, |
|
"ك": 38, |
|
"ل": 39, |
|
"م": 40, |
|
"ن": 41, |
|
"ه": 42, |
|
"و": 43, |
|
"ى": 44, |
|
"ي": 45, |
|
"ً": 46, |
|
"ٌ": 47, |
|
"ٍ": 48, |
|
"َ": 49, |
|
"ُ": 50, |
|
"ِ": 51, |
|
"ّ": 52, |
|
"ْ": 53 |
|
}, |
|
"ardzoff": { |
|
"[PAD]": 55, |
|
"[UNK]": 54, |
|
"e": 1, |
|
"h": 2, |
|
"i": 3, |
|
"k": 4, |
|
"n": 5, |
|
"o": 6, |
|
"s": 7, |
|
"u": 8, |
|
"|": 0, |
|
"ء": 9, |
|
"آ": 10, |
|
"أ": 11, |
|
"ؤ": 12, |
|
"إ": 13, |
|
"ئ": 14, |
|
"ا": 15, |
|
"ب": 16, |
|
"ة": 17, |
|
"ت": 18, |
|
"ث": 19, |
|
"ج": 20, |
|
"ح": 21, |
|
"خ": 22, |
|
"د": 23, |
|
"ذ": 24, |
|
"ر": 25, |
|
"ز": 26, |
|
"س": 27, |
|
"ش": 28, |
|
"ص": 29, |
|
"ض": 30, |
|
"ط": 31, |
|
"ظ": 32, |
|
"ع": 33, |
|
"غ": 34, |
|
"ـ": 35, |
|
"ف": 36, |
|
"ق": 37, |
|
"ك": 38, |
|
"ل": 39, |
|
"م": 40, |
|
"ن": 41, |
|
"ه": 42, |
|
"و": 43, |
|
"ى": 44, |
|
"ي": 45, |
|
"ً": 46, |
|
"ٌ": 47, |
|
"ٍ": 48, |
|
"َ": 49, |
|
"ُ": 50, |
|
"ِ": 51, |
|
"ّ": 52, |
|
"ْ": 53 |
|
}, |
|
"kab": { |
|
"$": 1, |
|
"0": 2, |
|
"1": 3, |
|
"2": 4, |
|
"3": 5, |
|
"4": 6, |
|
"5": 7, |
|
"6": 8, |
|
"7": 9, |
|
"8": 10, |
|
"9": 11, |
|
"[PAD]": 58, |
|
"[UNK]": 57, |
|
"a": 12, |
|
"b": 13, |
|
"c": 14, |
|
"d": 15, |
|
"e": 16, |
|
"f": 17, |
|
"g": 18, |
|
"h": 19, |
|
"i": 20, |
|
"j": 21, |
|
"k": 22, |
|
"l": 23, |
|
"m": 24, |
|
"n": 25, |
|
"o": 26, |
|
"p": 27, |
|
"q": 28, |
|
"r": 29, |
|
"s": 30, |
|
"t": 31, |
|
"u": 32, |
|
"v": 33, |
|
"w": 34, |
|
"x": 35, |
|
"y": 36, |
|
"z": 37, |
|
"|": 0, |
|
"é": 38, |
|
"ï": 39, |
|
"č": 40, |
|
"ţ": 41, |
|
"ǧ": 42, |
|
"ɛ": 43, |
|
"ɣ": 44, |
|
"γ": 45, |
|
"ε": 46, |
|
"σ": 47, |
|
"ԑ": 48, |
|
"ḅ": 49, |
|
"ḍ": 50, |
|
"ḥ": 51, |
|
"ṛ": 52, |
|
"ṣ": 53, |
|
"ṭ": 54, |
|
"ẓ": 55, |
|
"€": 56 |
|
} |
|
} |
|
|