Choosing A Speech Recognition Model

Electrical Engineering students built and programmed a robotic hand to translate spoken language into ASL fingerspelling. During the development of the NLP block, they researched and tested several different speech recognition libraries, evaluating them based on accuracy, speed, and memory usage. Kaldi is an open-source C++ library that is extendable and modular, but has a long installation and build process. DeepSpeech is an open-source Speech-To-Text engine using a model trained by machine learning techniques based on the TensorFlow framework, but lacks documentation and features.