In this line, https://github.com/eladhoffer/seq2seq.pytorch/blob/348276b2fcc5a60352b3dccaae7102666dbbd4ac/seq2seq/tools/beam_search.py#L216, the decrease of num_hyp will increase the value of k, which then leads to the out-of-bounds for the words[idx][k], I don't know why you use num_hyp?
