Other languages than english, teach the software to use someone's voice

[TCH68k]

I would like to ask two questions about Tacotron 2:

• Is it possible to synthesize speech with it in any other language than english? If yes, how?

• Is it possible to train the software to use someone's voice from recorded WAV (or other format) files? If yes, how?

I've used this tutorial: https://pytorch.org/hub/nvidia_deeplearningexamples_tacotron2/