{'|': 0, "'": 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, 'q': 19, 'r': 20, 's': 21, 't': 22, 'u': 23, 'v': 24, 'w': 25, 'x': 26, 'y': 27, 'z': 28, 'à': 29, 'ç': 30, 'è': 31, 'é': 32, 'ê': 33, 'ë': 34, 'î': 35, 'ï': 36, 'ô': 37, 'û': 38, 'â': 39, '[UNK]': 40, '[PAD]': 41, '<s>': 42, '</s>': 43}