add tokenizer

vocab.json

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