I want to create czech language model

Hey, I saw that mozilla TTS doesnt support czech language and I would like to create an open source for it. Anybody who wants to collaborate?

I am a newbie when it comes to machine learning but I have been picking up information quite fast and since the processes are already outlined by a few ppl in discussions etc. it hopefully shouldnt be a big issue except for getting the data set. I saw a lot of data here https://commonvoice.mozilla.org/en/datasets?fbclid=IwAR0Y0B2ydmGEBkwqHlBIYODPtqfsgFTG6YLb8hR6Pl3FV6wDZ7k45Yc1nPg but there are no transcripts there so I already started looking elsewhere.