Ryan Leary
Ryan Leary
Any progress here? Is losing the parameter tying only an issue if you want to continue training from a checkpoint? i.e. I have trained models on a GPU, I'm happy...
A few follow up questions: 1. I see that we obtain a per-character log-likelihood as the output of the rnn: `prediction = lst[#lst]`. For scoring purposes, If the input sequence...
@JohnReid I did get it working. If you look at the closed PR (#61) you can see the implementation I used. It hasn't been rebased on any of the changes...
@JohnReid I've added you as a collaborator on my fork of the repo. If you made improvements to the script and wouldn't mind pushing them to a branch, I'd greatly...
Please hold off merge of this until we make sure neural type information is included in nemo files.
Linking this with #83. Thanks for submitting the PR. I have a few requested changes, then we'll get it merged.
Please file separate issues for the other things you mentioned. I think some of them can be handled rather straightforwardly.
Not at this time, no. PRs are welcomed.
Are you creating a new scorer each time per chance? We don't do a whole lot of dynamic memory allocation.
Test added, thanks!