add tokenizer

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

vocab.json

@@ -1 +1 @@
-{"(": 1, ")": 2, "*": 3, "a": 4, "b": 5, "c": 6, "d": 7, "e": 8, "f": 9, "g": 10, "h": 11, "i": 12, "j": 13, "k": 14, "l": 15, "m": 16, "n": 17, "o": 18, "p": 19, "r": 20, "s": 21, "t": 22, "u": 23, "v": 24, "w": 25, "x": 26, "y": 27, "á": 28, "é": 29, "í": 30, "ó": 31, "ú": 32, "–": 33, "’": 34, "|": 0, "<unk>": 35, "<pad>": 36, "<s>": 37, "</s>": 38}
+{"(": 1, ")": 2, "a": 3, "b": 4, "c": 5, "d": 6, "e": 7, "f": 8, "g": 9, "h": 10, "i": 11, "j": 12, "k": 13, "l": 14, "m": 15, "n": 16, "o": 17, "p": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "á": 27, "é": 28, "í": 29, "ó": 30, "ú": 31, "’": 32, "|": 0, "<unk>": 33, "<pad>": 34, "<s>": 35, "</s>": 36}