add tokenizer

vocab.json

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