# Model Maker Role

Last update: Mar 7, 2024


#

# Requirements

# Before proceeding, ensure you meet these requirements.
#
REQUIREMENTS
  • Model's .PTH file.
  • Model's .INDEX file.
  • General information about the model.
  • General information about its training process.
  • A Hugging Face account.
  • At least 1 audio sample of the model WITH NO MUSIC.
#

# Things to Avoid

# This will disqualify your post

# It lacks the correct files.

  • The .ZIP file must contain both the correct .INDEX & .PTH file. Learn about them here.

#

# Model is low quality.

  • A bad model sounds:

    • Scratchy/screechy.
    • Muffled.
    • Inaccurate to the source.
    • Incapable of hitting certain notes.
    • With slurred speech.
    • Unable of pronouncing words correctly in its intended language.
    • With artifacting.

#

# An outdated extraction method was used.

  • Only Mangio-Crepe & RMVPE are allowed. Learn about them here

  • Harvest, Dio, Crepe-Tiny, PM, etc. are obsolete.


#

# The audio demo has an instrumental.

  • Don't include ANY music on the audio demo, even if it's not copyrighted. This is due to:

    • Concerns over copyright.
    • In many cases, the music can "hide" the flaws of the voice models, making it harder to judge the quality of the model.

# The audio demo is altered.

  • Don't add reverb, equalize, or alter the demo in any way, as that won't be a faithful representation of the model. It must be the raw, unmodified output from RVC.

  • Trimming silences at the beginning/end of the audio is valid.

#

#

# Steps

# Step 1: Zip the model.

  • Gather the .PTH & .INDEX file and zip them into a .ZIP file.

  • It must be a .ZIP file, not .7ZIP or .RAR.


#

# Step 2: Upload it.

  • The ZIP must be stored in Hugging Face in a public repo of openrail license.

  • Learn how here.


#

# Step 3: Prepare the submission.

  • Once your model is ready, head over to the #get-model-maker channel.

  • Type the /submit command of QCBot and click the command.

image

# Now fill up the information about your model:

modelname
Its name.
rvc
Version of RVC it was trained on (will almost always be v2).
extraction
The extraction method you used.
epochs
Total epochs amount.
link
Its download link from Hugging Face.
image
Image of what it represents (person/character).
demo
Audio sample of it talking/singing.
note
Optional. Add more context about the model if you want.


#

# Step 4: Send submission.

  • Once you are done filling the information, send the message.

  • If everything went fine, your submission will be added to the queue & the bot will send a confirmation message, containing your submission ID.
    With the ID you can:

    • Check your submission's number in queue with the command /queue followed by the ID. (e.g /queue 251).
    • Cancel your submission with the command /cancel followed by the ID.
  • Now wait for a Model QC (quality checker) to verify your model. You'll be notified once it has been reviewed.

  • If your model gets approved, the bot will notify you with something like this:

    image

  • You can then repost the model (& future models) to the #voice-models forum.


#

# You have reached the end.

Report Issues