add tokenizer

vocab.json

@@ -1 +1 @@
-{"é": 0, "z": 1, "p": 2, "w": 3, "t": 4, "g": 5, "0": 6, "q": 7, "ñ": 8, "n": 9, "m": 10, "a": 11, "f": 12, "d": 13, "s": 14, "h": 15, "6": 16, "i": 18, "u": 19, "8": 20, "v": 21, "l": 22, "y": 23, "b": 24, "7": 25, "2": 26, "o": 27, "e": 28, "'": 29, "4": 30, "5": 31, "r": 32, "9": 33, "j": 34, "k": 35, "c": 36, "1": 37, "x": 38, "3": 39, "|": 17, "[UNK]": 40, "[PAD]": 41}
+{"7": 0, "'": 1, "q": 2, "z": 3, "5": 4, "h": 5, "n": 6, "x": 7, "6": 8, "o": 9, "f": 10, "4": 11, "1": 12, "y": 13, "j": 14, "u": 15, "r": 16, "d": 17, "w": 18, "m": 19, "9": 20, "k": 21, "é": 22, "2": 23, "a": 24, "8": 25, "v": 26, "3": 28, "l": 29, "0": 30, "s": 31, "ñ": 32, "i": 33, "p": 34, "g": 35, "c": 36, "b": 37, "e": 38, "t": 39, "|": 27, "[UNK]": 40, "[PAD]": 41}