English

fairseq S2T: Fast Speech-to-Text Modeling with fairseq

Computation and Language 2022-06-15 v2 Audio and Speech Processing

Abstract

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.

Keywords

Cite

@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)

R2 v1 2026-06-23T19:14:46.761Z