[feature request] add nbest option to top-k / top-p (nucleus sampling) generation

[vince62s]

This option would enable to re-rank nbest hypotheses generated with nucleus sampling.

[PC91]

Hello @vince62s,
I would like to know if this feature is already implemented. I am also interested and I could give it a try.
Thank you.

[vince62s]

It is not implemented yet.
I recently revamped beam_search.py and you can check where we use n_best to make sure we add enough hypotheses. You can easily do the same in greed_search.py it is not difficult, if you have issues let me know.