Open sourcing wav2letter++, the fastest state-of-the-art speech system, and flashlight, an ML library going native by/via via @fbOpenSource

The Facebook AI Research (FAIR) Speech team is sharing the first fully convolutional speech recognition system. It uses convolutional neural networks (CNNs) for acoustic modeling and language modeling, and is reproducible. The team says that wav2letter++ is composed only of convolutional layers, which yields performance that’s competitive with recurrent architectures.

There are two articles linked of the landing page from the links in this post. This reads as a great achievement and looks very interesting.