add tokenizer

vocab.json

@@ -1 +1 @@
-{"o": 0, "æ": 1, "ê": 2, "]": 3, "x": 4, "b": 5, ")": 6, "é": 7, "—": 8, "j": 9, "”": 10, "y": 11, "w": 12, "l": 13, "z": 14, "“": 16, "n": 17, "d": 18, "£": 19, "t": 20, "g": 21, "p": 22, "[": 23, "r": 24, "c": 25, "'": 26, "(": 27, "s": 28, "m": 29, "i": 30, "f": 31, "a": 32, "v": 33, "ô": 34, "u": 35, "k": 36, "h": 37, "&": 38, "_": 39, "‘": 40, "’": 41, "q": 42, "e": 43, "|": 15, "[UNK]": 44, "[PAD]": 45}
+{"d": 0, "z": 1, "p": 2, "x": 3, "k": 4, "w": 5, "'": 6, "&": 7, "j": 8, "a": 9, "c": 10, "q": 11, "f": 12, "m": 13, "g": 14, "i": 15, "t": 16, "r": 17, "v": 18, "h": 19, "y": 20, "l": 21, "u": 22, "b": 23, "s": 24, "e": 25, "o": 27, "n": 28, "|": 26, "[UNK]": 29, "[PAD]": 30}