We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide end-to-end workflows from data pre-processing, model training to offline (online) inference. We implement state-of-the-art RNN-based, Transformer-based as well as Conformer-based models and open-source detailed training recipes. Fairseq's machine translation models and language models can be seamlessly integrated into S2T workflows for multi-task learning or transfer learning. Fairseq S2T documentation and examples are available at https://github.com/pytorch/fairseq/tree/master/examples/speech_to_text.
@article{arxiv.2010.05171,
title = {fairseq S2T: Fast Speech-to-Text Modeling with fairseq},
author = {Changhan Wang and Yun Tang and Xutai Ma and Anne Wu and Sravya Popuri and Dmytro Okhonko and Juan Pino},
journal= {arXiv preprint arXiv:2010.05171},
year = {2022}
}
Comments
Post-conference updates (accepted to AACL 2020 Demo)