add tokenizer

vocab.json

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