What is the resource to run this project

[JohnHerry]

Thanks for the good job.
I am trying to reproducing the result on LJSpeech dataset. I have two GPU card with atmost 10G GPU memory left each. The training process run to epoch7 and crashed because of "Out of Memory"; I had tried to cut the batchsize to harf: 64, that makes no sense. I did not change the model hyper params to prevent the model degeneration. So what should I do to run it up?
Or is there a list of limitations about resources to run the training process up?