# Model Maker Role

Last update: May 20, 2024


# Requirements

# Before proceeding, ensure you meet these 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.
    • Has a muffled sound.
    • Sounds inaccurate to the source.
    • Is incapable of hitting certain notes.
    • Has slurred speech.
    • Is unable of pronouncing words correctly in its intended language.
    • Has artifacting.


# An outdated extraction method was used.

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

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


# The audio demo contains instrumental.

  • Don't include ANY music in 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 model, making it harder to judge its quality.

# The audio demo is altered.

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

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



# 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 a Hugging Face public repository 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.


# Now fill up the information about your model:

Its name.
The technology used for its training.
The extraction method you used.
Total epochs amount.
Its download link from Hugging Face.
An image of what it represents (person/character).
An audio sample of it talking/singing.
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 this 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 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 a message like this:


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


# You have reached the end.

Report Issues