add tokenizer

vocab.json

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