Speech Extensions to Fairseq – Dmytro Okhonko
Language translation and audio processing are critical components in systems and applications such as search, translation, speech, and assistants. Fairseq, a framework for sequence-to-sequence applications such as language translation, has been extended to include support for end-to-end learning for speech and audio recognition tasks. These extensions enable faster exploration and prototyping of new speech research ideas while offering a clear path to production.
