nanoLLM & Riva Client compatibility issue

Robotics & Edge Computing Jetson Systems Jetson Orin Nano
,
1

Good Afternoon,

Jetson Orin Nano Super running on JP R36.4.4

Latest version of Riva Arm64

Riva Client per “jetson-containers run dustynv/riva-client:python-r36.2.0”

nanoLLM per “dustynv/nano_llm:r36.4.0”

when trying to add RivaASR through the graphic interface I get the terminal error message:

TypeError: RivaASR.state_dict() got an unexpected keyword argument ‘config’

Any idea on how to solve this?

Regards,

Jucova

2

*** Please note that this reply is generated by LLM automatically ***

Good afternoon!

I’ve analyzed the provided context and your question. It appears that you’re experiencing an issue with adding Riva ASR through the graphic interface on your Jetson Orin Nano Super, which is running on JP R3644 with the latest version of Riva Arm64.

The error message you’re encountering is not explicitly stated in your question, but I’ll provide some general guidance and potential solutions based on the context.

  1. Riva Client and Riva ASR compatibility: Ensure that the Riva Client (r3620) and Riva ASR versions are compatible with each other and with the JetPack version (R3644) you’re using. You can check the NVIDIA Riva documentation for compatibility information.
  2. Container configuration: Verify that the dustynv/riva-client:python-r3620 and dustynv/nano-llm:r3640 containers are properly configured and running on your Jetson Orin Nano Super. You can check the container logs for any errors or issues.
  3. Graphic interface issue: The error might be related to the graphic interface or the web browser you’re using to access the Riva ASR interface. Try using a different browser or check the browser’s console logs for any errors.
  4. Riva ASR configuration: Ensure that the Riva ASR configuration is correct and complete. You can check the Riva ASR documentation for configuration guidelines.
  5. Jetson Orin Nano Super resources: Verify that your Jetson Orin Nano Super has sufficient resources (e.g., memory, CPU) to run the Riva ASR service. You can check the system resources using tools like htop or nvidia-smi.

To further troubleshoot the issue, you can try the following:

  • Check the Riva Client and Riva ASR logs for any errors or issues.
  • Run the Riva ASR service in debug mode to get more detailed error messages.
  • Try adding Riva ASR through the command-line interface instead of the graphic interface.

If none of these suggestions help, please provide more details about the error message you’re encountering, and I’ll do my best to assist you further.

*** Please give the thumbs up if you get answers you like. Or provide feedback to help us improve the answer. ***

5

Hi,

Could you share more details about how you meet this error?
Is there any steps we can try to reproduce this?

Based on the Dockerfile, the riva-client is built with the below GitHub:

Could you try to use the latest source to see if the issue still there?

Thanks.

7

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