PhoWhisper: Automatic Speech Recognition for Vietnamese

Thanh-Thien Le, Linh The Nguyen, Dat Quoc Nguyen

3/27/2024

eess.AScs.CL

Official code: VinAIResearch/PhoWhisper (249 stars, BSD-3-Clause, last commit 2024-11-12).

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

View on arXiv View PDF

Code Implementations(1)

VinAIResearch/PhoWhisperOfficial100%

BSD-3-Clause

PhoWhisper: Automatic Speech Recognition for Vietnamese (2024)

24927Feb 21, 20241 years agoBSD-3-Clause

Similar Papers

ViSpeechFormer: A Phonemic Approach for Vietnamese Automatic Speech Recognition

85% match2026

Whisper based Cross-Lingual Phoneme Recognition between Vietnamese and English

84% match2025

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining

84% match2025

TSPC: A Two-Stage Phoneme-Centric Architecture for code-switching Vietnamese-English Speech Recognition

83% match2025

VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain

81% match1 repo3792024

VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition

81% match2024

Cite this paper

@article{le2024phowhisper,
  title  = {PhoWhisper: Automatic Speech Recognition for Vietnamese},
  author = {Thanh-Thien Le and Linh The Nguyen and Dat Quoc Nguyen},
  year   = {2024},
  eprint = {2406.02555},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.02555v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/2406.02555.svg)](https://codeofpaper.com/paper/2406.02555)