add tokenizer

vocab.json

@@ -1 +1 @@
-{"l": 0, "z": 1, "r": 2, "x": 3, "'": 4, "j": 5, "y": 6, "b": 7, "q": 8, "v": 9, "w": 10, "g": 12, "d": 13, "o": 14, "f": 15, "u": 16, "n": 17, "m": 18, "a": 19, "p": 20, "k": 21, "s": 22, "e": 23, "h": 24, "c": 25, "i": 26, "t": 27, "|": 11, "[UNK]": 28, "[PAD]": 29}
+{"y": 0, "b": 1, "k": 2, "m": 3, "d": 4, "u": 5, "l": 6, "s": 7, "w": 8, "q": 9, "v": 10, "p": 11, "z": 12, "a": 13, "j": 14, "t": 15, "h": 16, "n": 17, "g": 18, "'": 19, "r": 21, "x": 22, "i": 23, "f": 24, "o": 25, "e": 26, "c": 27, "|": 20, "[UNK]": 28, "[PAD]": 29}