https://github.com/yl4579/StyleTTS2
Inference using Demo/Inference_LibriTTS.ipynb from the repo above. Just change the model and reference audio to those in the current repo.
Example of produced tts - https://www.youtube.com/watch?v=Tuz7_7q0Pr0
Also check out this cool autism project I did - https://github.com/Shiro836/forsen_ai_api \