add tokenizer

vocab.json

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