fairseq S2T: Fast Speech-to-Text Modeling with fairseq
international joint conference on natural language processing, pp. 33-39, 2020.
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 implem...More
PPT (Upload PPT)