add tokenizer

vocab.json

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