Posting Models to AI Hub by FDG

You will need

• General information regarding your model
• The .pth file of the model
• The .index file of the model
• LV. 1 or higher in AI Hub
• A Huggingface account
• Audio demos of your model

Step 1

Get the files you need for your model

Your model needs to be packed into a zip file with its final .pth and its added___.index file.

Google Colab users can get this file by running Step 4 on the colab, then checking /RVC_Backup/Finished/ for the model zip.

For local users, you can find these files in the weights folder and the logs folder, respectively.

Once you have located both of these files, they need to be packed into a .zip file. IT MUST BE A ZIP FILE, RAR OR 7Z WILL NOT WORK

Step 2

Prepare huggingface for your files

Create a huggingface account if you haven't already. Once you are logged into huggingface, click on your account icon in the top-right corner, and hit new model

From here, you will be asked how to set up your model repository, which is where ALL of your models will be stored. You can name your repo as you please, but make sure it is set to public and the license is openrail*.

Once the repository has been created, locate the Add file button above the file list and select Upload files

You will be prompted to select your files to upload. You can either click on the upload box to browse to your zip file, or simply drag and drop it into the box.

After queueing your zip file(s) for uploading, Hit the Commit changes to main button at the bottom.

Once its done uploading, you should automatically be brought back to the file list. From here, right-click on the download icon next to the model's name and click on copy link.

Step 3

Submitting the model to AI Hub

Once your model is ready, you can submit it in #⁠get-model-maker-role using the /submit command of QCBot (or /submitkits for Kits models).
While using the command, please fill in the following informations about your model:

• modelname: The name of your model
• rvc: v1 or v2 (optional for Kits models)
• extraction: The extraction method used for training (optional for Kits models)
• epochs: The number of epochs of your model (optional for Kits models)
• link: the Huggingaface link of your model (or Kits link if you're using /submitkits)
• image: An image for your model
• demo: An audio demo of your character either speaking or singing
• note: (optional)

Please note that you can only attach one audio demo file using the command. If you wish to include more, you can just send them after the bot confirmation response.

If everything went fine, your submission will be added to the queue and the bot will send a confirmation message, containing your submission ID. You'll need this ID if you want to:

1. Check your submission's number in queue with /queue [ID]
2. Cancel your submission with /cancel [ID]

From here, you can wait for a Model QC to verify your model. You'll be notified once it has been reviewed. You can then repost your model (and any future models) to the forum #voice-models

Step 4

Congrats

You did it! You successfully posted a model to AI Hub, where it can be appreciated by many.