Faster than real-time! Based on Mozilla's DeepSpeech Engine 0.6.1.
https://www.hackster.io/dmitrywat/offline-speech-recognition-on-raspberry-pi-4-with-respeaker-c537e7

In this video we’re going to run and benchmark Mozilla’s DeepSpeech ASR (automatic speech recognition) engine on different platforms, such as Raspberry Pi 4(1 GB), Nvidia Jetson Nano, Windows PC and Linux PC.

The hardware for this video was kindly provided by Seeed studio, check out the ReSpeaker USB Mic Array and other hardware at Seeed studio store!
https://www.seeedstudio.com/ReSpeaker-USB-Mic-Array-p-4247.html
https://www.seeedstudio.com/Raspberry-Pi-4-Computer-Model-B-1GB-p-4078.html

Blog articles about DeepSpeech engine:
https://hacks.mozilla.org/2019/12/deepspeech-0-6-mozillas-speech-to-text-engine/
https://hacks.mozilla.org/2017/11/a-journey-to-10-word-error-rate/

Mozilla's DeepSpeech Github
https://github.com/mozilla/DeepSpeech

Add me on LinkedIn if you have any questions:
https://www.linkedin.com/in/dmitry-maslov-ai/

Credits for music:
https://www.youtube.com/watch?v=IjJSWtE3pOE
Portal 2 - Love as a Construct (Alex Giudici Remix) V2