U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF

U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF

25 April 2024

Binbin Zhang

Chao Yang

Papers citing "U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF"

7 / 7 papers shown

Title
BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR Guodong Ma Wenxuan Wang Lifeng Zhou Yuting Yang Yuke Li Binbin Du MoE 72 0 0 22 Jan 2025
HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models Bingshen Mu Kun Wei Qijie Shao Yong Xu Lei Xie MoE 34 1 0 30 Sep 2024
Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing Hukai Huang Shenghui Lu Yahui Shan He Qu Wenhao Guan Q. Hong Lin Li MoE 23 0 0 26 Jul 2024
Accelerating Parallel Sampling of Diffusion Models Zhiwei Tang Jiasheng Tang Hao Luo Fan Wang Tsung-Hui Chang 30 11 0 15 Feb 2024
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages Yu Zhang Wei Han James Qin Yongqiang Wang Ankur Bapna ... Pedro J. Moreno Chung-Cheng Chiu J. Schalkwyk Franccoise Beaufays Yonghui Wu VLM 77 249 0 02 Mar 2023
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference Sneha Kudugunta Yanping Huang Ankur Bapna M. Krikun Dmitry Lepikhin Minh-Thang Luong Orhan Firat MoE 119 104 0 24 Sep 2021
Scaling Laws for Neural Language Models Jared Kaplan Sam McCandlish T. Henighan Tom B. Brown B. Chess R. Child Scott Gray Alec Radford Jeff Wu Dario Amodei 223 4,424 0 23 Jan 2020