Readme
RVC v2 Dataset Creation Tool
Introduction
Create vocal datasets for Realistic Voice Cloning (RVC) v2 models with ease. Simply provide a YouTube video URL and let the tool handle the extraction and preparation of vocal data, ideal for training sophisticated voice cloning models. π§ π€
Features
- Easy Input: Paste the URL and optionally name your dataset. π
- Automated Processing: Isolates vocals and segments them into clips. βοΈ
- Immediate Download: Access your dataset with a click. πΎ
How to Use
- YouTube URL: Input the link to the video. ποΈ
- Dataset Name: Choose a name or stick with the default. βοΈ
- Run: Hit βRunβ to begin the magic. π
- Download: Grab your
.zip
file full of vocal clips. π¦
What You Get
- The output is a
.zip
file titleddataset/<your_dataset_name>/
. - It houses
split_<i>.mp3
files, each containing a clear vocal extract. πΆ
Training Your Model
Once you have your dataset, head over to https://replicate.com/zsxkib/train-rvc-v2
to train your RVC v2 model on your newly created dataset. π
Acknowledgments
This tool is adapted from work by the talented ardha27, who authored the initial codebase available here. π