add tokenizer

vocab.json

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