Riva virtual assistant, anifest for nvcr.io/nvidia/riva/riva-speech-client:1.6.0-beta-samples not found

Hardware - Jetson Nano
Operating System: Ubuntu 18.04
Riva Version: 1.6.0-beta

Hi
I’ d like to follow the steps HERE to create a virtual assistant (only client sample application) on Jetson Nano.
Since Riva only supports Volta, Turing and A100 GPU, I will host Riva service on the GPU server later.

I get an error and have no idea what’s wrong over here.
Error response from daemon: manifest for nvcr.io/nvidia/riva/riva-speech-client:1.6.0-beta-samples not found: manifest unknown: manifest unknown
when downloading image from NGC via
docker pull nvcr.io/nvidia/riva/riva-speech-client:1.6.0-beta-samples

Any advice? thanks.

Hi @ryan_lin
Could you please try the latest 1.7-beta-samples?

docker pull nvcr.io/nvidia/riva/riva-speech-client:1.7.0-beta-samples

https://docs.nvidia.com/deeplearning/riva/user-guide/docs/samples/weather.html#running-the-demo

Thanks

HI @SunilJB
Thanks, the new docker image works. But when I try to run the service within Docker container via
docker run -it --rm -p 8009:8009 nvcr.io/nvidia/riva/riva-speech-client:1.7.0-beta-samples /bin/bash
It shows error

WARNING: The requested image's platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested
standard_init_linux.go:228: exec user process caused: exec format error

Does that mean this client sample is not allowed to be hosted on Jetson Nano?
I though only Riva-server-services have to be hosted on GPU server with Volta, Turing and A100 GPU.
In this case, how could I plug my headset (as the voice input) to the server on the cloud?

Hi Ryan,

Yes, currently Jetson platform is not supported but client-sample can be executed on any desktop/server systems.

Thanks

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.