add tokenizer

vocab.json

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