add tokenizer

vocab.json

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