That being said, some enhancements added compared to the original repo: :heavycheckmark: Possible to train in other languages :heavycheckmark: Hifigan added, allowing for faster inference at the cost of quality. :heavycheckmark: whisper-v3 added as a chooseable option for whisperx :heavycheckmark: Output conversion using RVC This is a fork of the repo originally located here: https://git.ecker.tech/mrq/ai-voice-cloning.