ereday
ereday
## 🐛 Bug Hi, I was trying to evaluate the pre-trained models under "Efficient Wait-k Models for Simultaneous Machine Translation". For this, I followed the instructions given in the [readme](https://github.com/elbayadm/attn2d/blob/master/examples/waitk/README.md#download-pre-trained-models)....
Hi, When I run your code on multi-gpu, performance degrades severely (compared to the single-gpu version). To make the code multi-gpu competable, I've only added 2 lines of code: *...
Hi, In Section 5, it is said that : > For each task, we train a separate model, starting with sequences of complexity 6 and incrementing by 4 once it...