Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

HELP WANTED!!!!!!!!!!! #235

Open
21sK1p opened this issue May 3, 2024 · 3 comments
Open

HELP WANTED!!!!!!!!!!! #235

21sK1p opened this issue May 3, 2024 · 3 comments

Comments

@21sK1p
Copy link

21sK1p commented May 3, 2024

Can we add a checkpoint to the styleTTS2 model to finetune the model from the last epoch we trained?
As I am using the free version of Colab, I can only finish my data to 5 epochs. After that, I exceeded my GPU limit, and all my data was saved in my drive, but then I had to start training it again from the start. I want to train it from my last checkpoint (last epoch trained). I asked if we could add a checkpoint to the model for the above query, just like tortoiseTTS
(I asked blackbox.ai, and it says we can, but I need clarification on it)?
cc @yl4579 @astricks @kmn1024 @eltociear @kmn1024

@21sK1p 21sK1p changed the title Resume finetuning Resume finetuning May 6, 2024
@21sK1p 21sK1p changed the title Resume finetuning HELP WANTED!!!!!!!!!!! May 7, 2024
@godspirit00
Copy link

Just edit the config to point the pretrained model to your last checkpoint, and set load_only_params to false.

@21sK1p
Copy link
Author

21sK1p commented May 9, 2024

Just edit the config to point the pretrained model to your last checkpoint, and set load_only_params to false.

it is not working. I tried what you said, but it is not working.
@godspirit00

@Karesto
Copy link

Karesto commented May 10, 2024

Could you give us your config and the command you're running ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants