add tokenizer

vocab.json

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