fairseq s2t: Fast speech-to-text modeling with fairseq
In this reference
A fairseq extension for speech-to-text tasks such as recognition and translation, with workflows from data preprocessing onward.
Cite the original work
C. Wang & Y. Tang & X. Ma & A. Wu & D. Okhonko… (2020). fairseq s2t: Fast speech-to-text modeling with fairseq [Research paper]. arXiv. https://arxiv.org/pdf/2010.05171
View BibTeX
@misc{fairseq_s2t,
author = {C. Wang and Y. Tang and X. Ma and A. Wu and D. Okhonko…},
title = {{fairseq s2t: Fast speech-to-text modeling with fairseq}},
howpublished = {arXiv},
url = {https://arxiv.org/pdf/2010.05171},
year = {2020}
}
