JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT
Abstract
JoeyS2T is a JoeyNMT extension for speech-to-text tasks such as automatic speech recognition and end-to-end speech translation. It inherits the core philosophy of JoeyNMT, a minimalist NMT toolkit built on PyTorch, seeking simplicity and accessibility. JoeyS2T's workflow is self-contained, starting from data pre-processing, over model training and prediction to evaluation, and is seamlessly integrated into JoeyNMT's compact and simple code base. On top of JoeyNMT's state-of-the-art Transformer-based encoder-decoder architecture, JoeyS2T provides speech-oriented components such as convolutional layers, SpecAugment, CTC-loss, and WER evaluation. Despite its simplicity compared to prior implementations, JoeyS2T performs competitively on English speech recognition and English-to-German speech translation benchmarks. The implementation is accompanied by a walk-through tutorial and available on https://github.com/may-/joeys2t.
Keywords
Cite
@article{arxiv.2210.02545,
title = {JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT},
author = {Mayumi Ohta and Julia Kreutzer and Stefan Riezler},
journal= {arXiv preprint arXiv:2210.02545},
year = {2022}
}
Comments
EMNLP 2022 demo track