add tokenizer

vocab.json

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