I have ROS2 implemented on my UNO Q and my voice manager node is using Vosk for speech to text.
This is working well except that I feel the accuracy is not as good as I had hoped.
Going to get a better microphone later this week but curious if anyone has implemented Whisper and, if so, how big of a hit did it have on resources?
Please make a tutorial so that following the steps of that tutorial, I can exactly get the output without asking further questions.
Thanks,
Are you looking for steps on setting up ROS2 or implementing Vosk?
To convert speech into text using UNO Q.
I went ahead and implemented Whisper and it’s really no better, getting a new microphone tomorrow.