add tokenizer

vocab.json

@@ -1 +1 @@
-{"w": 0, "ë": 1, ")": 2, "g": 3, "o": 4, "é": 5, "h": 6, "ş": 7, "ı": 8, "ö": 9, "y": 10, "m": 11, "q": 12, "k": 13, "j": 14, "'": 15, "s": 16, "z": 17, "ğ": 18, "̇": 19, "r": 20, "û": 21, "(": 22, "ç": 23, "c": 25, "d": 26, "â": 27, "n": 28, "t": 29, "x": 30, "u": 31, "ü": 32, "a": 33, "l": 34, "î": 35, "…": 36, "’": 37, "p": 38, "v": 39, "e": 40, "i": 41, "b": 42, "f": 43, "|": 24, "[UNK]": 44, "[PAD]": 45}
+{"n": 0, "y": 1, "e": 2, "̇": 3, ")": 4, "h": 5, "(": 6, "p": 7, "x": 8, "i": 9, "…": 10, "'": 11, "t": 12, "r": 13, "b": 14, "j": 15, "ü": 16, "â": 17, "ç": 18, "q": 20, "v": 21, "k": 22, "ë": 23, "f": 24, "m": 25, "g": 26, "w": 27, "î": 28, "d": 29, "s": 30, "o": 31, "ş": 32, "u": 33, "z": 34, "û": 35, "a": 36, "ğ": 37, "’": 38, "ö": 39, "c": 40, "l": 41, "ı": 42, "é": 43, "|": 19, "[UNK]": 44, "[PAD]": 45}