Skip to content

How to continue fine tuning of model? #10

Closed

Description

@TaoTeCha

How can I continue training on one of my finetuned models? I'm using google colab so it was only about to run to 36k steps before stopping. I see that there is a generator and a discriminator model, how will this work when continuing fine tuning? Do I just load in the generator and lose the training for the discriminator?

I tried to start again, just feeding the path of my finetuned G model instead of ljs_base, but the quality is considerably worse and seems like it started training nearly from the beginning.

Thanks!

Activity

  1. changed the title [-]Labels for training output values?[/-] [+]How to continue fine tuning of model?[/+] on Jun 22, 2021
  2. TaoTeCha commented on Jun 22, 2021

    @TaoTeCha
    Author

    Nevermind. Since I am using google colab I had to change model_dir, and on the second run I pointed it to a different folder than the first. Just don't download the base model and use the same model_dir. It will pick up the checkpoints.

  3. ToiYeuTien commented on Oct 18, 2023

    @ToiYeuTien

    Hi !
    I have trained on my computer a Vietnamese female voice model in 500k steps. and I found the voice quite clear. I want to train another male Vietnamese voice.
    I learned there is a training method based on a previously trained model, which will shorten the training time.
    Can you help me with that method.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions