What tools do you use to create/split file lists for new dataset?

Please advise as per subject.

You should have some file prepared where wavs paths are assigned with texts. Then run preprocess script as written in step 4 of "Pre-requisites" to convert text to IPA phonemes. Note that you must have eSpeak installed correctly.
Resulting .cleaned file you just split manually into train (95%) and valid (5%) filelists, set paths to them in your config.json