Oliver Adams

Sorry about that, I've changed it back. I shouldn't have been working on master directly.

I just pushed a check in train_batch_gen() that throws an exception if the Corpus has no training utterances. I'm removing the bug status now, I'll keep the issue open since...

When this is done, I can point the README.md to readthedocs.

Thanks! Fortunately most of this is embarrassingly parallel.

The import error is probably what needs more investigation. The code does support CUDA. Perhaps the issue is that you have CUDA 11.0 installed and the version of tensorflow used...

Yeah we can bump the version to something that supports the newer versions of CUDA. If 1.15.0 works for you @mirfan899 then maybe we go with that.

Speaking mostly for the ESPnet recipes here, I think there's a good argument for not bothering with this feature. The argument is that the vast majority of the time is...

I also ran into this issue when training on the `mask` branch: ``` ... File "/media/cat/oadams/yolov7/train.py", line 363, in train loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) # loss scaled by...