add tokenizer

vocab.json

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