Lennart Brocki

I would like to fine-tune your WaveRNN pretrained model (800k steps on LJSpeech) to my own dataset. First of all, can this be expected to work? Also, if I understand...

To speed up the computation for obtaining smoothed masks, the noisy samples are created first and gradients are obtained as a single batch for all the noisy samples. Afterwards the...

In this [notebook](https://github.com/hila-chefer/Transformer-MM-Explainability/blob/main/Transformer_MM_explainability_ViT.ipynb) for creating the explanations for ViT there was a memory leak in the function ```generate_relevance```. This PR fixes that.