Building a Text-to-Speech system using Tacotron2 -- 2

I want to build a speech synthesis system (TTS) for the Kurdish language. I have collected data according to Tacotron's requirement for an audio text pair. I need to configure the environment and build the model to train Tacotron on the data I have collected. There are two projects that can be used, please find the link to both projects below. And I'm open to new suggestions as well.

https://espnet.github.io/espnet/
https://github.com/NVIDIA/tacotron2