
A simple and effective approach to scaling speech recognition models using Mixture-of-Experts (MoE) layers, achieving Dense-1B level accuracy with Dense-225M level inference cost, while also enabling streaming capabilities.


coremsg

scaling-large-speech-recognition-models-with-mixture-of-experts-achieving-dense-1b-accuracy-at-dense-225m-inference-cost


Scaling Large Speech Recognition Models with Mixture-of-Experts: Achieving Dense-1B Accuracy at Dense-225M Inference Cost
