Variable Scale Pruning for Transformer Model Compression in End-to-End Speech Recognition

Variable Scale Pruning for Transformer Model Compression in End-to-End Speech Recognition

Transformer models are being increasingly used in end-to-end speech recognition systems for their performance. However, their substantial size poses challenges for deploying them in real-world applications. These models heavily rely on attention and feedforward layers, with the latter containing a v...

Full description

Bibliographic Details
Main Authors: Leila Ben Letaifa, Jean-Luc Rouas
Format: Article
Language:English
Published: MDPI AG 2023-08-01
Series:Algorithms
Subjects:
model compression
variable scale pruning
end-to-end speech recognition
transformer architecture
weight magnitude
Online Access:https://www.mdpi.com/1999-4893/16/9/398

Internet

https://www.mdpi.com/1999-4893/16/9/398

Similar Items