Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

1 code implementation • 18 Sep 2023 • George August Wright, Umberto Cappellazzo, Salah Zaiem, Desh Raj, Lucas Ondel Yang, Daniele Falavigna, Mohamed Nabih Ali, Alessio Brutti

In self-attention models for automatic speech recognition (ASR), early-exit architectures enable the development of dynamic models capable of adapting their size and architecture to varying levels of computational resources and ASR performance demands.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2