add tokenizer

vocab.json

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