Riva_quickstart 1.8 using "de_DE" setting in config on DGX workstation

Please provide the following information when requesting support.

Hardware - GPU (4x V100)
Hardware - CPU DGX Workstation
Operating System
Riva Version 1.8

How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)

Download riva_quickstart_1.8-beta with cli
cd dir and open config
set language_code to “de-DE”
set nlp & tts to false as stated in config comment

$ bash riva_init.sh

leads to:

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

NVIDIA Release 21.12 (build 30304770)

Copyright (c) 2018-2021, NVIDIA CORPORATION. All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION. All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying
project or file.

NOTE: Legacy NVIDIA Driver detected. Compatibility mode ENABLED.

2022-01-04 13:20:20,872 [INFO] Writing Riva model repository to ‘/data/models’…
2022-01-04 13:20:20,872 [INFO] The riva model repo target directory is /data/models
2022-01-04 13:20:24,918 [WARNING] Property ‘encrypted’ is deprecated. Please use ‘encryption’ instead.
2022-01-04 13:20:24,918 [WARNING] Property ‘binary’ is deprecated. Please use the callback system instead.
2022-01-04 13:20:25,790 [ERROR] Traceback (most recent call last):
File “/opt/conda/lib/python3.8/site-packages/servicemaker/cli/deploy.py”, line 84, in deploy_from_rmir
rmir = RMIR.restore_from(model_filename, encryption_key=model_key)
File “/opt/conda/lib/python3.8/site-packages/servicemaker/rmir/rmir.py”, line 275, in restore_from
rmir._read()
File “/opt/conda/lib/python3.8/site-packages/servicemaker/rmir/rmir.py”, line 202, in _read
setattr(self.config, name, all_args[name])
KeyError: ‘model_class’

  • echo

  • echo ‘Riva initialization complete. Run ./riva_start.sh to launch services.’
    Riva initialization complete. Run ./riva_start.sh to launch services.

and

$ bash riva_start.sh

leads to:

Starting Riva Speech Services. This may take several minutes depending on the number of models deployed.
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
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
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
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
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

logs are attached
config.sh (7.5 KB)
docker.log (29.8 KB)

Same setup is working on DGX A100.

Takes a long time and warnings and errors along the way. But is working right now.

2022-01-04 14:45:55,183 [INFO] Building TRT engine from ONNX file
[W] colored module is not installed, will not use colors when logging. To enable colors, please install the colored module: python3 -m pip install colored
[W] ‘Shape tensor cast elision’ routine failed with: None
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:604] Reading dangerously large protocol message. If the message turns out to be larger than 2147483647 bytes, parsing will be hity reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:81] The total number of bytes read was 564431790
[TensorRT] WARNING: onnx2trt_utils.cpp:362: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[TensorRT] WARNING: Detected invalid timing cache, setup a local cache instead

Detected invalid timing cache, setup a local cache instead
Internal error: cannot reformat, disabling format. Try decreasing the workspace size with IBuilderConfig::setMaxWorkspaceSize().