The reviewed record of science sign in
Pith

arxiv: 2406.02555 · v1 · pith:ASHJPPGJ · submitted 2024-03-27 · eess.AS · cs.CL

PhoWhisper: Automatic Speech Recognition for Vietnamese

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ASHJPPGJrecord.jsonopen to challenge →

classification eess.AS cs.CL
keywords phowhispervietnameseautomaticrecognitionspeechaccentsachievedbenchmark
0
0 comments X
read the original 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

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.