English

PhoWhisper: Automatic Speech Recognition for Vietnamese

Audio and Speech Processing 2024-06-06 v1 Computation and Language

Abstract

We introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the Whisper model on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. We have open-sourced PhoWhisper at: https://github.com/VinAIResearch/PhoWhisper

Cite

@article{arxiv.2406.02555,
  title  = {PhoWhisper: Automatic Speech Recognition for Vietnamese},
  author = {Thanh-Thien Le and Linh The Nguyen and Dat Quoc Nguyen},
  journal= {arXiv preprint arXiv:2406.02555},
  year   = {2024}
}

Comments

Accepted to ICLR 2024 Tiny Papers Track

R2 v1 2026-06-28T16:53:20.815Z