natural-language-processing-11
Simultaneous Speech-to-Text Translation
3260 papers • 126 benchmarks • 313 datasets
Simultaneous Speech-to-Text translation aims to translate concurrently with the source speech. It is crucial since it enables real-time interpretation of conversations, lectures and talks.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in simultaneous-speech-to-text-translation-11
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find simultaneous-speech-to-text-translation-11 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit
Shinji Watanabe, J. Pino, Siddharth Dalmia, Zhaoheng Ni, Xiaohui Zhang, Yifan Peng, Patrick Fernandes, Brian Yan, Jiatong Shi, Yun Tang, H. Inaguma, Peter Pol'ak, Dan Berrebbi, Tomoki Hayashi, Moto Hira, Soumi Maiti•Sun Apr 09 2023
The overall design, example models for each task, and performance benchmarking behind ESPnet-ST-v2 are described, which is publicly available at https://github.com/espnet/esp net.
21