Lead AI Research Engineer
In recent years, Transducers have become the dominant ASR model architecture, surpassing CTC and LAS model architectures. In this article, we will examine the Transducer architecture more closely, and compare it to the more common CTC model architecture.
This week’s Deep Learning Research paper is “Deep Shallow Fusion for RNN-T Personalization.”
As part of our core research and development efforts to continue pushing the state of the art of speech recognition accuracy, in this post, we explore speech recognition architectures that are gaining new popularity in both academia and industry settings.
The complete guide on how to build an end-to-end Speech Recognition model in PyTorch. Train your own CTC Deep Speech model using this tutorial.