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
How to train new Waveglow model for diffirent language? #189
Comments
Just prepare your language specific wav files for training |
@EuphoriaCelestial have you succeed to train your own model for your own language ? |
Yes I have successfully trained my model, but there are some errors in output audio, I am still working on it. |
@EuphoriaCelestial thanks for response, can you tell how you achieved this ? Can you show any wiki or documentation to follow ? |
actually, I just follow those steps in README file, its pretty simple if your audio matched the default sample rate, bit rate, ... |
Finally I installed project successfully with all it's dependencies and I've synthesized a voice with pre trained model. But I found out that training a model is pretty time consuming. I have core I7 9th gen, 16gb ram, 6 gb gpu, I understood that it's very poor hardware to train, what do you recommend to train a model? Any free cloud solutions? Can tell how long it takes to train model for instance for you and your hardware? Thanks |
yeah it will take a long time. I have RTX 2080ti with 11gb VRAM and it take few days. I have not tried any cloud solutions yet so I cant give any advice. |
Unable to run train.py : Can you help me, please? |
just comment out the line, you can add it back the next time you generate a checkpoint. |
@EuphoriaCelestial, I've installed successfully, how many hours (minimum) of audio need to generate correct spelled audio ? |
I dont know the minimum, I havent tested because it will take a lot of time and effort |
And one more question: and starting but iteration starts again from 1. How to start iteration from 80000? |
why does your checkpoint saved with .pt? |
I thought it should have the suffix pt, so I renamed it. How else do I create a pt file from a checkpoint? |
The inference code can load the checkpoint directly so I dont have to export pt file from checkpoint
it will work if you rename it to |
When I train waveglow, this message appears to me with each new epoch: |
I've never encounter this problem before, maybe you should create a new issue so the creators can help. |
As the title, I would like to know how to train a new model using another dataset, which have the same structure as LJ Speech dataset. What modifications need to be done for a diffirent language?
The text was updated successfully, but these errors were encountered: