Voice detection - Audio training

Hi everyone !

I am currently working on a project with 2 friends, which basically consists out of building/ using a voice recognition software for short commands to order a multi-meter connected with a USB-RS232 cable to a NanoJetson. (Jetson Nano Developer Kit)

We have already settled the Jetson Nano environment on windows with PuTTY, read a lot of articles written by NVIDIA (Voice Detection, Voice Training in the ISAAC help pages) and tried to figure out most of it. (even tried to understand how to create a voice detection software fully with Tensorflow, which I still don’t understand what it is ^^’).

Here is the problem : we never did such a project, we never touched anything related to these kinds of programming projects (like never used Raspberry Pi), and thus when it comes to read those pages we don’t really get any of the instructions (a lot about SDKs, epochs, …).

Could some one that has time to loose help 3 poor students lost in this vague programming world?
We would actually just love to understand how to install ISAA, iot use it on the Jetson, how to even run a program or write it on the Jetson and how the Jetson can recognize external devices ?

Thank you a lot in advance for your time !
SYM Team