add tokenizer

vocab.json

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