add tokenizer

vocab.json

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