add tokenizer

vocab.json

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