add tokenizer

vocab.json

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