← authors · overview

• OWSM V3.1: Better And Faster Open Whisper-style Speech Models Based On E-branchformer
  2024 · 104 citations
• Reproducing Whisper-style Training Using An Open-source Toolkit And Publicly Available Data
  2023 · 72 citations
• Self-supervised Speech Representations Are More Phonetic Than Semantic
  2024 · 72 citations
• Exploring Speech Recognition, Translation, And Understanding With Discrete Speech Units: A Comparative Study
  2023 · 71 citations
• One Model To Rule Them All ? Towards End-to-end Joint Speaker Diarization And Speech Recognition
  2023 · 36 citations