ㅤㅤ👇 Applio's official links below 👇ㅤㅤ
🌐 Website • 📚 Documentation • ☎️ Discord
Goal of this project is for me to have a much more flexible base than mainline rvc.
ㅤ
Features that are, at the time of writing, already added in:
-
Support for 'Spin' and perhaps soon.. wavlm feature extraction.
Needs proper pretrains. They are in work. -
Ability to choose an optimizer.
( Currently supporting: AdamW, RAdam, Ranger21 ) -
Double-update strategy for Discriminator.
-
Support for custom input-samples used during training for live-preview / live evaulation of model's performance.
-
Mel spectrogram %-based similarity metric.
-
Choice of using either Multi-scale mel loss or classic L1.
( Optimized. ) -
Support for the following vocoders: HiFi-GAN, MRF-HiFi-gan and Refine-GAN.
( And their respective pretrains. ) -
Checkpointing and various speed / memory optimizations compared to RVC.
-
New logging mechanism for losses: Average loss per epoch logged as the standard loss,
and rolling average loss over 50 steps to evaluate general trends and the model's performance over time. -
Ability to quickly change the learning rate of Generator And Discriminator.
-
Configurable lr warmup.
⚠️ 1: HiFi-gan is the stock rvc/applio vocoder, hence it's what you use for og pretrains and hifigan-based customs.
⚠️ 2: MRF-HiFi-GAN and Refine-GAN require new pretrained models. They can't be used with original rvc's G/D pretrains.
✨ to-do list ✨
- Ability to choose lr_decay from the ui.
💡 Ideas / concepts 💡
- Propably improving the mel-similarity.. or generally expanding the idea.
- and more.. perhaps ..
Run the installation script based on your operating system:
- Windows: Double-click
run-install.bat. - Linux/macOS: Execute
run-install.sh.
Start Applio using:
- Windows: Double-click
run-fork.bat. - Linux/macOS: Run
run-fork.sh.
In cases of having inference errors / issues on MacBooks or other M1, M2 and M3 devices:
Uncomment the " export OMP_NUM_THREADS=1 " line in in the " run-fork.sh " file.
This launches the Gradio interface in your default browser.
To monitor training or visualize data:
- Windows: Run
run-tensorboard.bat. - Linux/macOS: Run
run-tensorboard.sh.
For more detailed instructions, visit the documentation.
The creators of the original Applio repository, Applio's contributors, and the maintainer of this fork (Codename;0), built upon Applio, are not responsible for any legal issues, damages, or consequences arising from the use of this repository or the content generated from it. By using this fork, you acknowledge that:
- The use of this fork is at your own risk.
- This repository is intended solely for educational, and experimental purposes.
- Any misuse, including but not limited to illegal activities or violation of third-party rights,
is not the responsibility of the original creators, contributors, or this fork’s maintainer. - You willingly agree to comply with this repository's Terms of Use