add tokenizer

vocab.json

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