Mozilla DeepSpeech
Download from github
DeepSpeech is an open source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Speech research paper. The engine operates offline so connection to the Internet is not needed. Can run on a Raspberry Pi 4.

A TensorFlow implementation of Baidu’s DeepSpeech architecture

License: Mozilla Public License 2.0
Authors: Mozilla