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.

Sign up for GitHub

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

Jump to bottom

mixed precision 학습 관련 #224

Open

laetokang opened this issue Mar 4, 2024 · 0 comments

laetokang commented Mar 4, 2024

❓ Questions & Help

Transducer (RNN-T, Conformer-T) 계열 모델로 학습하려고 하는데 학습 시간이 오래 걸려서 mixed precision 사용하려고 합니다.

계속 아래와 같은 에러가 발생하는데, Transducer 모델은 이 방법을 사용할 수 없는걸까요?

RuntimeError: Input and parameter tensors are not the same dtype, found input tensor with Float and parameter tensor with Half

Details

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