Open zacharymacleod opened 5 years ago
The samples shown are generated using --bidirectional_eachstep
flag. I updated the repository recently so that the flag wasn't true by default. This was done to reduce the inference time. However, the quality suffers after a sentence or two.
So I've tried using the collab notebook for conditional generation, but the results are nowhere near as long or as good quality as the samples listed in the Medium article. They seem to lose coherency very quickly and start repeating phrases or single words repeatedly. What were the arguments used to create the samples?