Hi all,
My students and I wanted to use Mozilla’s DeepSpeech model on some of our robots, so we wrote a simple node to make the model available in ROS:
Functionality is fairly limited at the moment, but we’ve been happy with our testing so far and think that the system could be useful to others looking for a simple speech recognition solution that runs offline.
We’re currently planning the next iteration of this package, and would love to hear your thoughts if you try it out.
Thanks,
Richard