Tera2Space

Just use blender 2.9( i tested on it, and on 3.6) works perfectly in 2.9, in 3.6 i had same issue

Probably same problem as we have in pflow)

> @Tera2Space What was the problem? Code geass nice, problem was that it generate wrong aligment, i just though of reason: https://github.com/p0p4k/pflowtts_pytorch/issues/24#issuecomment-1983667975 in your model, what shape is input to...

> For a single batch - shapes look something like this: > > ``` > m_p torch.Size([32, 192, 74]) > x_mask torch.Size([32, 1, 74]) > y_mask torch.Size([32, 1, 293]) >...

> pflow it should be both textencoder how do you think we can improve pflow's encoder?

> I have uncommented code that you commented in constructor and in `forward` method and commented call to MAS. This works fine, it trains without crashes but inference crashes. But...

> No it doesn't crash during the training. I got crash after I loaded trained checkpoint on synthesis method. Is the error something like "out of memory"?

> > > No it doesn't crash during the training. I got crash after I loaded trained checkpoint on synthesis method. > > > > > > Is the error...

Yep, same, I believe that AlignerNet didn't converged so duration predictor learn wrong alignments so at inference audio become very long and cause out of memory.

> So, maybe try a small sentence inference? Does that work? If it does, then just memory issue and not code ksse. 1500 gibs of vram.... I think it's code...