WenetSpeech-Yue
收藏资源简介：
WenetSpeech-Yue是一个大规模的粤语语音语料库，包含多维度标注，适用于语音理解和生成任务。该数据集由西北工业大学音频、语音和语言处理小组创建，包含21800小时的语音数据，涵盖了10个不同的领域。数据集的标注包括ASR转录、文本置信度、说话者身份、年龄、性别、语音质量评分等。WenetSpeech-Yue是目前最大的开源粤语语音语料库，为粤语语音理解和生成提供了宝贵的资源。
WenetSpeech-Yue is a large-scale Cantonese speech corpus with multi-dimensional annotations, suitable for speech understanding and generation tasks. This dataset was created by the Audio, Speech and Language Processing Group of Northwestern Polytechnical University, containing 21,800 hours of speech data spanning 10 distinct domains. Its annotations include ASR transcriptions, text confidence scores, speaker identity, age, gender, and speech quality ratings, among others. WenetSpeech-Yue is currently the largest open-source Cantonese speech corpus, providing a valuable resource for Cantonese speech understanding and generation.
WeNet 数据集概述
基本信息
- 名称：WeNet
- 许可协议：Apache 2.0
- 编程语言：Python 3.7 或 3.8
核心特点
- 生产优先且生产就绪：核心设计原则，提供全栈生产解决方案用于语音识别。
- 准确：在多个公共语音数据集上实现SOTA结果。
- 轻量：易于安装、使用，设计良好且文档完善。
安装与使用
Python包安装
sh pip install git+https://github.com/wenet-e2e/wenet.git
命令行使用
sh wenet -m paraformer audio.wav
- 中文模型选项：
paraformer、firered、wenetspeech - 英文模型选项：
whisper-large-v3、whisper-large-v3-turbo
Python编程使用
python import wenet model = wenet.load_model(paraformer) result = model.transcribe(audio.wav) print(result.text)
训练与部署安装
- 克隆仓库：
git clone https://github.com/wenet-e2e/wenet.git - 创建Conda环境：Python 3.10
- 安装CUDA：推荐CUDA 12.1
- 安装Torch和TorchAudio：推荐版本2.2.2+cu121
昇腾NPU用户
- 安装CANN工具包和内核
- 安装WeNet与torch-npu依赖
- 版本控制要求详见文档
运行时构建
- 需要CMake 3.14或更高版本
- 支持x86运行时和语言模型（LM）
支持与交流
- 通过GitHub Issues讨论
- 中文用户可通过微信公众号和微信群交流
致谢
- 借鉴ESPnet的基于Transformer的建模代码
- 借鉴Kaldi的基于WFST的LM集成解码代码
- 参考EESEN构建基于TLG的LM集成图
- 参考OpenTransformer实现端到端模型的Python批量推理
引用文献
bibtex @inproceedings{yao2021wenet, title={WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit}, author={Yao, Zhuoyuan and Wu, Di and Wang, Xiong and Zhang, Binbin and Yu, Fan and Yang, Chao and Peng, Zhendong and Chen, Xiaoyu and Xie, Lei and Lei, Xin}, booktitle={Proc. Interspeech}, year={2021}, address={Brno, Czech Republic}, organization={IEEE} }
@article{zhang2022wenet, title={WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit}, author={Zhang, Binbin and Wu, Di and Peng, Zhendong and Song, Xingchen and Yao, Zhuoyuan and Lv, Hang and Xie, Lei and Yang, Chao and Pan, Fuping and Niu, Jianwei}, journal={arXiv preprint arXiv:2203.15455}, year={2022} }
- 1WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation西北工业大学 · 2025年
