Can I read PhoWhisper: Automatic Speech Recognition for Vietnamese on EtoBox?

PhoWhisper: Automatic Speech Recognition for Vietnamese by Le, Thanh-Thien; Nguyen, Linh The; Nguyen, Dat Quoc is a scholarly article available to read on EtoBox.

What is PhoWhisper: Automatic Speech Recognition for Vietnamese about?

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

Author

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

Published

2024

Language

EN