add tokenizer

vocab.json

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