Picture for Daniel Bikel

Daniel Bikel

Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency

Add code
Nov 05, 2023
Figure 1 for Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
Figure 2 for Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
Figure 3 for Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
Viaarxiv icon