This paper describes the ESPnet Unsupervised ASR Open-source Toolkit (EURO), an end-to-end open-source toolkit for unsupervised automatic speech recognition (UASR). EURO adopts the state-of-the-art UASR learning method introduced by the Wav2vec-U, originally implemented at FAIRSEQ, which leverages self-supervised speech representations and adversarial training. In addition to wav2vec2, EURO extends the functionality and promotes reproducibility for UASR tasks by integrating S3PRL and k2, resulting in flexible frontends from 27 self-supervised models and various graph-based decoding strategies. EURO is implemented in ESPnet and follows its unified pipeline to provide UASR recipes with a complete setup. This improves the pipeline's efficiency and allows EURO to be easily applied to existing datasets in ESPnet. Extensive experiments on three mainstream self-supervised models demonstrate the toolkit's effectiveness and achieve state-of-the-art UASR performance on TIMIT and LibriSpeech datasets. EURO will be publicly available at https://github.com/espnet/espnet, aiming to promote this exciting and emerging research area based on UASR through open-source activity.

中文翻译：

---

EURO：ESPnet 无监督 ASR 开源工具包

本文介绍了 ESPnet 无监督 ASR 开源工具包 (EURO)，这是一种用于无监督自动语音识别 (UASR) 的端到端开源工具包。EURO 采用了 Wav2vec-U 引入的最先进的 UASR 学习方法，该方法最初在 FAIRSEQ 上实施，该方法利用自监督语音表示和对抗训练。除了 wav2vec2 之外，EURO 还通过集成 S3PRL 和 k2 扩展了 UASR 任务的功能并提高了可重复性，从而产生了来自 27 个自监督模型和各种基于图形的解码策略的灵活前端。EURO 在 ESPnet 中实施，并遵循其统一管道为 UASR 配方提供完整的设置。这提高了管道的效率，并允许 EURO 轻松应用于 ESPnet 中的现有数据集。对三种主流自监督模型的广泛实验证明了该工具包的有效性，并在 TIMIT 和 LibriSpeech 数据集上实现了最先进的 UASR 性能。EURO 将在 https://github.com/espnet/espnet 上公开，旨在通过开源活动促进这个基于 UASR 的令人兴奋的新兴研究领域。