VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain
To load labeled data, please refer to our HuggingFace, Paperswithcodes.
For full dataset (labeled data + unlabeled data) and pre-trained models, please refer to Google Drive
Please check "config" folder for reproducibility.
Necessary packages for GMM-HMM ASR: RETURNN, Sisyphus, RASR, SRILM, Fairseq.
You may also want to check how to fine-tune our wav2vec 2.0-based pre-trained models here.
If any links are broken, please contact me for fixing!
Le Duc Khai
University of Toronto, Canada
Email: duckhai.le@mail.utoronto.ca
GitHub: https://github.com/leduckhai