Unable to download RIVA models during riva_init.sh

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

Hardware - GPU:A100
Hardware - CPU
Operating System-Ubuntu 20.04
Riva Version-2.3
TLT Version (if relevant)
How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)

Hi,
I have been trying to use RIVA ASR models through the RIVA Speech Skills repo. But due to the following issue that occurs when running bash riva_init.sh:
Url: ‘https://authn.nvidia.com/token?service=ngc&scope=group/ngc:nvidia&scope=group/ngc:nvidia/riva’ is not reachable.

Is this due to a network issue at the server end? If not, please provide a solution for this.

2

Hi @mahima1

Thanks for your interest in Riva

Apologies you are facing the issue

For the error line you have attached guessing it to be a problem with the network side of things,

Is your machine under some firewall/proxy (that may block or restrict connections) ?

Can you run the below command and share with us the output

curl -Ivv  https://authn.nvidia.com

It may also be indicative of a problem with docker network, can you also please share the complete log output of command bash riva_init.sh in this thread

Thanks

3

Thank you for your respons @rvinobha.

I will have to confirm about the firewall/proxy settings at our end.

The output of the command shared by you is as follows:
"* Uses proxy env variable https_proxy == ‘https://10.7.9.47:9090/’

  • Trying 10.7.9.47:9090…
  • TCP_NODELAY set
  • Connected to 10.7.9.47 (10.7.9.47) port 9090 (#0)
  • ALPN, offering http/1.1
  • successfully set certificate verify locations:
  • CAfile: /etc/ssl/certs/ca-certificates.crt
    CApath: /etc/ssl/certs
  • TLSv1.3 (OUT), TLS handshake, Client hello (1):
  • error:1408F10B:SSL routines:ssl3_get_record:wrong version number
  • Closing connection 0
    curl: (35) error:1408F10B:SSL routines:ssl3_get_record:wrong version number"

The complete log output of the bash riva_init.sh is as follows:
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.
Image nvcr.io/nvidia/riva/riva-speech:2.5.0 exists. Skipping.
Image nvcr.io/nvidia/riva/riva-speech:2.5.0-servicemaker exists. Skipping.

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.
/bin/bash: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8)

==========================
=== Riva Speech Skills ===

NVIDIA Release (build 43645243)
Copyright (c) 2016-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

Copyright (c) 2018-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:

To install Python sample dependencies, run /opt/tensorrt/python/python_setup.sh

To install the open-source samples corresponding to this TensorRT release version
run /opt/tensorrt/install_opensource.sh. To build the open source parsers,
plugins, and samples for current top-of-tree on master or a different branch,
run /opt/tensorrt/install_opensource.sh -b
See GitHub - NVIDIA/TensorRT: NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications. for more information.

NOTE: CUDA Forward Compatibility mode ENABLED.
Using CUDA 11.6 driver version 510.47.03 with kernel driver version 450.191.01.
See CUDA Compatibility :: NVIDIA Data Center GPU Driver Documentation for details.

/bin/bash: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8)
/data/artifacts /opt/riva

Downloading nvidia/riva/rmir_asr_conformer_hi_in_str:2.5.0…
Url: ‘https://authn.nvidia.com/token?service=ngc&scope=group/ngc:nvidia&scope=group/ngc:nvidia/riva’ is not reachable.
Attempt 1 out of 3 failed
Trying again…
Url: ‘https://authn.nvidia.com/token?service=ngc&scope=group/ngc:nvidia&scope=group/ngc:nvidia/riva’ is not reachable.
Attempt 2 out of 3 failed
Trying again…
Url: ‘https://authn.nvidia.com/token?service=ngc&scope=group/ngc:nvidia&scope=group/ngc:nvidia/riva’ is not reachable.
Attempt 3 out of 3 failed
Error occurred downloading ‘nvidia/riva/rmir_asr_conformer_hi_in_str:2.5.0’. Exiting.
Error in downloading models."