Deploy ASR models on triton
#10327
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
-
Hello,
I want to deploy my fine-tuned FastConformer model on nvidia triton for batch inference and other functionalities.
Are there any guide or script to do ASR model deployment on triton server?
I know there are some scripts in nemo/deploy, but I believe these scripts are for llms implemented in NeMo.
Beta Was this translation helpful? Give feedback.
All reactions