"Waiting for Riva server to load all Models" Jetson Orin Nano

AI & Data Science Deep Learning (Training & Inference) Riva
,
1

Hi all!

I am trying to use Riva Speech to do live speech-to-text on my Jetson Orin Nano.

After following all of the quickstart guides quite closely, I am stuck with this error:

Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
<these messages repeat for a few minutes>
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Waiting for Riva server to load all models...retrying in 10 seconds
Health ready check failed.
Check Riva logs with: docker logs riva-speech

When I try to check the logs with “docker logs riva-speech” the command does not provide an output. No error, but also no content.

I have tried running riva_clean.sh followed by riva_init.sh to start fresh, but I run into the same problem.

Any help would be greatly appreciated, thanks so much! I really love this amazing community.

-Wes

2

Hi @sappington.wesley
Can you use a docker ps to check if the container is running?

Also wondering if the NVIDIA runtime working correctly in their Jetpack installation? You can check that with docker info command under “Runtimes” section.

Thanks,

Sophie