add tokenizer

vocab.json

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