add tokenizer

vocab.json

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