add tokenizer

vocab.json

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