Non-autoregressive approaches aim to improve the inference speed of
translation models by only requiring a single forward pass to generate the
output sequence instead of iteratively producing each predicted token.
Consequently, their translation quality still tends to be inferior to their
autoregressive counterparts due to several issues involving output token
interdependence. In this work, we take a step back and revisit several
techniques that have been proposed for improving non-autoregressive translation
models and compare their combined translation quality and speed implications
under third-party testing environments. We provide novel insights for
establishing strong baselines using length prediction or CTC-based architecture
variants and contribute standardized BLEU, chrF++, and TER scores using
sacreBLEU on four translation tasks, which crucially have been missing as
inconsistencies in the use of tokenized BLEU lead to deviations of up to 1.7
BLEU points. Our open-sourced code is integrated into fairseq for
reproducibility.

本文旨在改进非自回归方法在机器翻译方面的表现，探讨了多种技术提升其翻译质量和效率，并将其在四个翻译任务上进行了评估，考虑到 tokenized BLEU 的使用不一致，我们贡献了标准化的 BLEU、chrF++ 及 TER 得分，并将代码开源集成于 fairseq 中以便重现研究结果。

非自回归神经机器翻译：呼唤清晰度

Non-Autoregressive Neural Machine Translation: A Call for Clarity

This paper presents fairseq S^2, a fairseq extension for speech synthesis. We
implement a number of autoregressive (AR) and non-AR text-to-speech models, and
their multi-speaker variants. To enable training speech synthesis models with
less curated data, a number of preprocessing tools are built and their
importance is shown empirically. To facilitate faster iteration of development
and analysis, a suite of automatic metrics is included. Apart from the features
added specifically for this extension, fairseq S^2 also benefits from the
scalability offered by fairseq and can be easily integrated with other
state-of-the-art systems provided in this framework. The code, documentation,
and pre-trained models are available at
this https URL

本文介绍了 fairseq S^2，它是为语音合成设计的 fairseq 扩展，具备多种自回归和非自回归文本到语音模型及其多说话人变体。此外，还构建了多种预处理工具，以便使训练语音合成模型所需的数据更易获取。这篇论文还展示了一套自动度量标准，以方便进行快速的开发和分析。fairseq S^2 不仅具有为此扩展添加的特点，还受益于 fairseq 提供的可扩展性，并可以轻松地与该框架中提供的其他最先进的系统集成。

fairseq S^2: 一种可扩展且可集成的语音合成工具包

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

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 implement state-of-the-art
RNN-based, Transformer-based as well as Conformer-based models and open-source
detailed training recipes. Fairseq's machine translation models and language
models can be seamlessly integrated into S2T workflows for multi-task learning
or transfer learning. Fairseq S2T documentation and examples are available at
this https URL

Fairseq S2T 是一款扩展 fairseq 的语音转文本建模工具，具备可扩展和可扩展性设计，提供端到端的工作流程，支持 RNN-based, Transformer-based 和 Conformer-based 模型，并可以无缝集成多任务学习或迁移学习中的机器翻译模型和语言模型。

fairseq S2T: 使用 fairseq 进行快速语音转文本建模

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

fairseq is an open-source sequence modeling toolkit that allows researchers
and developers to train custom models for translation, summarization, language
modeling, and other text generation tasks. The toolkit is based on PyTorch and
supports distributed training across multiple GPUs and machines. We also
support fast mixed-precision training and inference on modern GPUs. A demo
video can be found at this https URL

fairseq 是一个开源的序列建模工具包，基于 PyTorch，支持在多个 GPU 和多台机器上训练自定义模型以进行翻译、摘要、语言建模和其他文本生成任务。