A Python tool specifically designed to split audio files into perfect segments of 5 sec. for creating RVC (Retrieval-based Voice Conversion) training datasets.
This tool solves a problem I've encountered during RVC model training: preparing audio datasets with consistent timing, clean segments. It automatically splits long audio files.
- Automatic Organization: Creates numbered files in organized folders
- Configurable Intervals: Easy to adjust segment duration (5s recommended for RVC as far as I know xd)
Keep in mind it's a very simple way to do it but feel free to collab :)