add tokenizer

vocab.json

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