{ "4": 1, "[PAD]": 92, "[UNK]": 91, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "g": 7, "h": 8, "i": 9, "k": 10, "l": 11, "m": 12, "n": 13, "o": 14, "p": 15, "q": 16, "r": 17, "s": 18, "t": 19, "u": 20, "v": 21, "x": 22, "y": 23, "|": 0, "à": 24, "á": 25, "â": 26, "ã": 27, "è": 28, "é": 29, "ê": 30, "ì": 31, "í": 32, "ò": 33, "ó": 34, "ô": 35, "õ": 36, "ù": 37, "ú": 38, "ý": 39, "ă": 40, "đ": 41, "ĩ": 42, "ũ": 43, "ơ": 44, "ư": 45, "ạ": 46, "ả": 47, "ấ": 48, "ầ": 49, "ẩ": 50, "ẫ": 51, "ậ": 52, "ắ": 53, "ằ": 54, "ẳ": 55, "ẵ": 56, "ặ": 57, "ẹ": 58, "ẻ": 59, "ẽ": 60, "ế": 61, "ề": 62, "ể": 63, "ễ": 64, "ệ": 65, "ỉ": 66, "ị": 67, "ọ": 68, "ỏ": 69, "ố": 70, "ồ": 71, "ổ": 72, "ỗ": 73, "ộ": 74, "ớ": 75, "ờ": 76, "ở": 77, "ỡ": 78, "ợ": 79, "ụ": 80, "ủ": 81, "ứ": 82, "ừ": 83, "ử": 84, "ữ": 85, "ự": 86, "ỳ": 87, "ỵ": 88, "ỷ": 89, "ỹ": 90 }