add tokenizer

vocab.json

@@ -1 +1 @@
-{"i": 0, "c": 1, "y": 3, "s": 4, "t": 5, "a": 6, "o": 7, "q": 8, "f": 9, "p": 10, "k": 11, "b": 12, "g": 13, "l": 14, "e": 15, "h": 16, "u": 18, "j": 19, "r": 20, "v": 21, "x": 22, "w": 23, "d": 24, "n": 25, "m": 26, "z": 27, "[UNK]": 28, "[PAD]": 29, "|": 17}
+{"h": 0, "j": 1, "b": 2, "k": 3, "f": 4, "r": 5, "p": 6, "o": 7, "a": 8, "v": 9, "y": 10, "e": 11, "n": 13, "s": 14, "g": 15, "z": 16, "q": 17, "d": 18, "u": 19, "l": 20, "c": 21, "w": 23, "x": 24, "i": 25, "t": 26, "m": 27, "[UNK]": 28, "[PAD]": 29, "|": 22}