Had

Get error then trying to plot this model https://drive.google.com/open?id=1QpcZb2nnzNmXAEm-DTBkRW2qKAb7hRq5 Code: https://colab.research.google.com/drive/1UR07U-9g115eLr2q83oojKThXqGzBtPY

How much time take tacotron gst infererence?/infererence stuck

6

It stuck on > Successfully opened dynamic library libcublas.so.10.0 Code https://colab.research.google.com/drive/10DxRZTqmIPE6983fGEZ2UDjRrcvM99pK

Cant use on pytorch 1.5/cuda 10.2 ImportError: libcudart.so.10.0: cannot open shared object file: No such file or directory

4

Google says this error cased by different versions of pytorch compiled and system cuda version. But it should be same https://i.imgur.com/u3GTFgv.png

Feature request for Disentangled Attention from DeBERTa

3

Paper in case you missed it. https://arxiv.org/abs/2006.03654

Weights from hugging face bert does not return same result

2

Here is notebook https://colab.research.google.com/drive/1Gn8SOLPVbMeFQ6voBd2fgUlaTqz3uVll?usp=sharing I checked code from both libs and didn't found a difference

Here is it, very noticeable artifacts  Here is demo https://colab.research.google.com/drive/1unDKzCr2wIrTISc9PzbHlwtXb1LSeFq9?usp=sharing

I have data with (batch, 80, sample len) shape, for now, I'm using SSIM with reshaping to (batch, 1, 80, sample len). But SSIM do not take into account zero...

Should you add compatibility with unusual models like gans for example

2

In general, I need some wrappers about how batch prcessed and data flow to model.