add tokenizer

vocab.json

@@ -1 +1 @@
-{"]": 0, "s": 1, "v": 2, "(": 3, "”": 4, "d": 5, "o": 6, "a": 7, "à": 8, "y": 9, "e": 10, "'": 11, "c": 12, "m": 13, "h": 14, "’": 15, "â": 16, ")": 17, "k": 18, "t": 19, "p": 20, "ü": 21, "“": 22, "r": 23, "x": 24, "g": 25, "é": 26, "w": 28, "n": 29, "i": 30, "b": 31, "z": 32, "u": 33, "q": 34, "ê": 35, "è": 36, "[": 37, "f": 38, "l": 39, "j": 40, "|": 27, "[UNK]": 41, "[PAD]": 42}
+{"é": 0, "v": 1, "c": 2, "x": 3, "t": 4, ")": 5, "f": 6, "”": 7, "n": 8, "q": 9, "[": 10, "j": 11, "r": 12, "g": 13, "b": 14, "]": 15, "o": 16, "m": 17, "w": 18, "a": 19, "à": 20, "e": 21, "“": 22, "i": 23, "(": 24, "ê": 25, "z": 26, "k": 27, "ü": 28, "s": 29, "h": 31, "u": 32, "d": 33, "l": 34, "'": 35, "p": 36, "y": 37, "|": 30, "[UNK]": 38, "[PAD]": 39}