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

Changhan Wang
Changhan Wang
Yun Tang
Yun Tang
Anne Wu
Anne Wu
Dmytro Okhonko
Dmytro Okhonko
Juan Pino
Juan Pino

international joint conference on natural language processing, pp. 33-39, 2020.

Cited by: 0|Views7

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 implem...More

Code:

Data:

Your rating :
0

 

Tags
Comments