Jetson Orin Nano and Riva

Robotics & Edge Computing Jetson Systems Jetson Orin Nano
1

I am trying to run the Riva examples on my Jetson Orin Nano Dev kit. I’m following these instructions: Local (Docker) — NVIDIA Riva but when I run riva_init.sh and enter my API key, the Riva Speech Server image is pulled, but then it fails to get the models.

jetson@jetson-nano:~/riva_quickstart_arm64_v2.19.0$ bash riva_init.sh
Please enter API key for ngc.nvidia.com:
Logging into NGC docker registry if necessary…
Pulling required docker images if necessary…
Note: This may take some time, depending on the speed of your Internet connection.

Pulling Riva Speech Server images.
Pulling nvcr.io/nvidia/riva/riva-speech:2.19.0-l4t-aarch64. This may take some time…

Downloading models (RMIRs) from NGC…
Note: this may take some time, depending on the speed of your Internet connection.
To skip this process and use existing RMIRs set the location and corresponding flag in config.sh.
wget: unable to resolve host address ‘api.ngc.nvidia.com’
unzip: cannot find or open ngccli_arm64.zip, ngccli_arm64.zip.zip or ngccli_arm64.zip.ZIP.
chmod: cannot access ‘ngc-cli/ngc’: No such file or directory
mv: cannot stat ‘ngc-cli/*’: No such file or directory
/opt/riva

bash: line 4: ngc: command not found
bash: line 4: ngc: command not found
bash: line 4: ngc: command not found

  • [[ tegra != \t\e\g\r\a ]]

  • [[ tegra == \t\e\g\r\a ]]

  • ‘[’ -d /home/jetson/riva_quickstart_arm64_v2.19.0/model_repository/rmir ‘]’

  • [[ tegra == \t\e\g\r\a ]]

  • ‘[’ -d /home/jetson/riva_quickstart_arm64_v2.19.0/model_repository/prebuilt ‘]’

  • echo

  • echo ‘Riva initialization complete. Run ./riva_start.sh to launch services.’
    Riva initialization complete. Run ./riva_start.sh to launch services.
    jetson@jetson-nano:~/riva_quickstart_arm64_v2.19.0$

Configuration:
Jetpack 6.2
Riva 2.19.0

3

Hi,

Do you enter the NGC API key correctly?
We have tested the script and it can work as expected in our environment.

$ sudo bash riva_init.sh
[sudo] password for nvidia: 
Please enter API key for ngc.nvidia.com: 
Logging into NGC docker registry if necessary...
Pulling required docker images if necessary...
Note: This may take some time, depending on the speed of your Internet connection.
> Pulling Riva Speech Server images.
  > Pulling nvcr.io/nvidia/riva/riva-speech:2.19.0-l4t-aarch64. This may take some time...
...
+ echo 'Riva initialization complete. Run ./riva_start.sh to launch services.'
Riva initialization complete. Run ./riva_start.sh to launch services.

Thanks.

4

I think my API key is correct. If I run riva_clean.sh, then riva_init.sh and enter a bad value for the API key, I get an error message. If I enter my API key correctly, it successfully downloads the first thing (Riva Speech Server images - nvcr.io/nvidia/riva/riva-speech:2.19.0-l4t-aarch64) but then fails on the next step: Downloading models (RMIRs) from NGC…

5

Hi,

Could you check which docker version you use?
If the version is v28+, please downgrade it to 27.5.1 and try it again.

$ sudo apt-get install -y docker-ce=5:27.5* docker-ce-cli=5:27.5* --allow-downgrades

Thanks.

6

I am currently running 27.5.1

jetson@jetson-nano:~$ docker info
Client: Docker Engine - Community
Version: 27.5.1
Context: default
Debug Mode: false
Plugins:
buildx: Docker Buildx (Docker Inc.)
Version: v0.20.0
Path: /usr/libexec/docker/cli-plugins/docker-buildx
compose: Docker Compose (Docker Inc.)
Version: v2.32.4
Path: /usr/libexec/docker/cli-plugins/docker-compose

Server:
Containers: 6
Running: 0
Paused: 0
Stopped: 6
Images: 4
Server Version: 27.5.1
Storage Driver: overlay2
Backing Filesystem: extfs
Supports d_type: true
Using metacopy: false
Native Overlay Diff: true
userxattr: false
Logging Driver: json-file
Cgroup Driver: systemd
Cgroup Version: 2
Plugins:
Volume: local
Network: bridge host ipvlan macvlan null overlay
Log: awslogs fluentd gcplogs gelf journald json-file local splunk syslog
Swarm: inactive
Runtimes: io.containerd.runc.v2 nvidia runc
Default Runtime: nvidia
Init Binary: docker-init
containerd version: 05044ec0a9a75232cad458027ca83437aae3f4da
runc version: v1.2.5-0-g59923ef
init version: de40ad0
Security Options:
seccomp
Profile: builtin
cgroupns
Kernel Version: 5.15.148-tegra
Operating System: Ubuntu 22.04.5 LTS
OSType: linux
Architecture: aarch64
CPUs: 6
Total Memory: 7.441GiB
Name: jetson-nano
ID: fd52b8ac-708b-46ef-9aed-003b50c6d749
Docker Root Dir: /var/lib/docker
Debug Mode: false
Experimental: false
Insecure Registries:
127.0.0.0/8
Live Restore Enabled: false

When I follow these steps to install the ngc cli for ARM64 Linux: https://org.ngc.nvidia.com/setup/installers/cli, the ngc setup seems successful. When I run the last step (ngc config set), I am entering these values:
API key: same API key that I entered when running riva_init.sh
CLI output format: what should this be? I’ve tried both ascii and json
org: I’ve entered the 16 digit number listed as my organization name
team: pressed Enter
ace: pressed Enter

these answers seem correct, based on the output below:
Validating configuration…
Successfully validated configuration.
Saving configuration…
Successfully saved NGC configuration to /home/jetson/.ngc/config

But I am still unable to successfully run the riva_init.sh script

7

Is this still an issue to support? Any result can be shared?

8

I am still unable to successfully complete the riva_init.sh script. After running “ngc config set”, I am able to complete the first step:

Pulling nvcr.io/nvidia/riva/riva-speech:2.19.0-l4t-aarch64. This may take some time…

but then it fails on the next step:

Downloading models (RMIRs) from NGC…
Note: this may take some time, depending on the speed of your Internet connection.
To skip this process and use existing RMIRs set the location and corresponding flag in config.sh.
wget: unable to resolve host address ‘api.ngc.nvidia.com’

Is there more configuration necessary when creating my personal API key? Is there another way to complete the steps in the riva_init.sh script?

10

Hi,

Could you follow the steps shared in the below comment to see if RIVA can work on your environment?

Thanks.

11

That seems to have fixed the problem for me. The riva_start.sh script runs to completion without errors. Thanks!

13

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