Operating System : Ubuntu 20.04
Riva Version:2.14.0
Jetson Xavier NX
Jetpack 5.1
Hi,
I’m having difficulty with Riva initialisation. The init command fails after around 30mins
during the RMIR model download with the following output
bash riva_init.sh config.sh
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:2.14.0-l4t-aarch64 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.
Error response from daemon: No such container: riva-models-download
Error in downloading models.
My config file is as follows:
config.txt (19.0 KB)
I tested docker could download successfully pull tensorflow, and so don’t think there is an issue with the docker configuration.
The models being downloaded are
gmr_speech_models:
nvidia/riva/models_asr_conformer_en_us_str:2.14.0-tegra-xavier
nvidia/riva/models_nlp_punctuation_bert_base_en_us:2.14.0-tegra-xavier
nvidia/riva/models_tts_fastpitch_hifigan_en_us_ipa:2.14.0-tegra-xavier
image_speech_api:
nvcr.io/nvidia/riva/riva-speech:2.14.0-l4t-aarch64\
Are there separate commands I can use to test these individually from command line, or check that these exist? I think this may help with the problem.
Many thanks in advance for any help provided.