# Codename Fork

Last update: July 4, 2025


#

# Introduction ‎

  • The codename fork is a fork of Applio made by Codename.

  • This fork has more features compared to others and changes to potentially increase quality.

  • Codename's fork is for advanced users, so if you don't know much about RVC then it's better if you use Applio.

  • This guide will be only talking about the new features since everything else has been covered in the Applio guide.


# Are RVC Models Safe?

RVC Models are PyTorch Models, a Python library used for AI. PyTorch uses serialization via Pythons' Pickle Module, converting the model to a file. Since pickle can execute arbitrary code when loading a model, it could be theoretically used for malware, but this fork has a built-in feature to prevent code execution along the model. Also, HuggingFace has a Security Scanner which scans for any unsafe pickle exploits and uses also ClamAV for scanning dangerous files.


# Pros & Cons

✔️ PROS
CONS
  • All of the pros of Applio.
  • Has a Warmup Phase option
  • Multiple optimizer choices
  • Mel similarity metric
  • SoX resampler
  • Hold-Out validation
  • TF32
  • More complicated features.

#

# Downloading

  1. Go to the github repo here. Then find the releases tab and click it.

    image

  2. Click on the zip file and download it. Then go into your C drive and extract it.

image
  1. Go into the codename fork folder and run the run-install.bat file then once it's done run go-fork.bat.

#

# New Features


# MRF HifiGAN & RefineGAN:

  • In the training section you are given the option to choose your vocoder
    • HiFi-GAN: the default vocoder for RVC.
    • MRF HiFi-GAN: a version of HiFi-GAN with MRF instead of MPD and new loss functions. This has higher fidelity but only works with this fork and the latest version Applio.
    • RefineGAN: an entirely new GAN which is in a experimental phase. This only works with this fork and Applio.
image

# Warmup Phase:

In the training section there is an option to enable a warmup phase and a slider to choose how long it lasts. Do not use this with Ranger21 or RAdam since they do this on their own.

image
  • The warmup phase is where the learning rate (lr) linearly increased for a certain amount of epochs, this can be used to prevent large destabilizing updates in the early stages of training.
    • There isn't much testing on what using a warmup in RVC does so expect varying results.

# Multiple Optimizers:

This fork gives you the option to choose between three optimizers.

  • AdamW
  • RAdam
  • Ranger21
image

# Custom LR for gen and disc:

In the training section under advanced there is a option to set a custom learning rate for both the generator and discriminator.

image

  • This controls how quickly or slowly either the gen or disc learn.

# TF32

TF32 (TensorFloat32) is a different precision to use instead of FP32 or BF16. This can give a speed boost. This is only supported on Ampere GPUs or newer.

image


# Upcoming Features:

  • Ability to delay / headstart the Generator or Discriminator.
  • Ability to choose lr_decay from the ui
  • And more...

#

# You have reached the end.

Report Issues