Jetson-voice: Please update PyTorch to remain compatible with later versions of NeMo

[vanessa.crosby]

Please provide the following information when requesting support.

Hardware - GPU (A100/A30/T4/V100): Xavier NX NVIDIA Volta GPU
Hardware - CPU 6-core NVIDIA Carmel ARMv8.2 64-bit
Operating System: linux4tegra Ubuntu 18.04
Riva Version jetson-voice Dustys repo
TLT Version (if relevant)
How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here):

in docker container run: examples/asr.py --model quartznet --wav data/audio/commands.wav

error:

[2021-12-10 07:00:38] audio.py:82 - loading audio 'data/audio/commands.wav'
[NeMo W 2021-12-10 07:00:38 patch_utils:50] torch.stft() signature has been updated for PyTorch 1.7+
    Please update PyTorch to remain compatible with later versions of NeMo.

This is not a show stopper but need best practices for dealing with this notice. Thanks!

[rleary]

I’d recommend filing a Github issue on that repository: GitHub - dusty-nv/jetson-voice: ASR/NLP/TTS deep learning inference library for NVIDIA Jetson using PyTorch and TensorRT