nipponjo

You can certainly do that. In the end, the models in this repo will learn a token ids -> mel frames mapping; independent of the language. In order to train...

I have re-uploaded the folders: [Places2](https://drive.google.com/drive/folders/1PHHGI-k-Z-cbP4jsXXs8ht7kBuvW_gg3?usp=sharing) [CelebA-HQ](https://drive.google.com/drive/folders/1cyPmpnCgB734mB3Ipk5rUPje7vVPCcGv?usp=sharing)

Hi, I have wanted to add some updates for a while. If you haven't already, you can take a look at the `exp` branch and the `training.md` file there. I...

Hello, yes, the input dimensions should be a multiple of 8, as the model performs an internal down- and up-sampling by a factor of 8, so otherwise the output and...