ESPnet-ST: All-in-One Speech Translation Toolkit
arXiv:2004.10234
Abstract
We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework. ESPnet-ST is a new project inside end-to-end speech processing toolkit, ESPnet, which integrates or newly implements automatic speech recognition, machine translation, and text-to-speech functions for speech translation. We provide all-in-one recipes including data pre-processing, feature extraction, training, and decoding pipelines for a wide range of benchmark datasets. Our reproducible results can match or even outperform the current state-of-the-art performances; these pre-trained models are downloadable. The toolkit is publicly available at https://github.com/espnet/espnet.
arXiv commentAccepted at ACL 2020 System Demonstration (update Table1, fix typo)
References in corpus (11)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- WaveNet: A Generative Model for Raw Audio
- Mixed Precision Training
- Training Tips for the Transformer Model
- How2: A Large-scale Dataset for Multimodal Language Understanding
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
- NeMo: a toolkit for building AI applications using Neural Modules
- wav2letter++: The Fastest Open-source Speech Recognition System
- Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
- RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
- Chainer: A Deep Learning Framework for Accelerating the Research Cycle