How to train new language XTTS V2

[JohnF51]

Hello, everybody,
I have a problem. I found one way to train a new language in XTTSV2 that is not supported yet. But I don't know how to achieve it. In the tutorial it says this:

2. Data Preparation
   Ensure your data is organized as follows:

project_root/
├── datasets/
│ ├── wavs/
│ │ ├── xxx.wav
│ │ ├── yyy.wav
│ │ ├── zzz.wav
│ │ └── ...
│ ├── metadata_train.csv
│ ├── metadata_eval.csv
│
├── recipes/
├── scripts/
├── TTS/
└── README.md
Format your metadata_train.csv and metadata_eval.csv files as follows:

audio_file|text|speaker_name
wavs/xxx.wav|How do you do?|@x
wavs/yyy.wav|Nice to meet you.|@y
wavs/zzz.wav|Good to see you.|@z

My problem is that I don't know how to create from voice wav, metadata_train.csv and metadata_eval.csv. I know that in finetunig training similar files are created but I don't know how to do it for my project. Can you give me any advice? I am using vscode, creating my own independent environment. Isn't there any github that can precompile data like this? I want to train the Slovak language which is very similar to the Czech language but there are some significant differences which I need to modify. Please if anyone knows please get in touch. Thank you