Parallel Distributed Deep Learning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
飞桨多语言OCR工具包（实用超轻量OCR系统，支持80+种语言识别，提供数据标注与合成工具，支持服务器、移动端、嵌入式及IoT设备端的训练与部署） Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
飞桨多模态集成与探索，支持主流多模态任务，涵盖端到端大规模多模态预训练模型及扩散模型工具箱，兼具高性能与灵活性。 Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.
All-in-One Development Tool based on PaddlePaddle
PaddleNLP是一款基于飞桨深度学习框架的大语言模型(LLM)开发套件，支持在多种硬件上进行高效的大模型训练、无损压缩以及高性能推理。PaddleNLP 具备简单易用和性能极致的特点，致力于助力开发者实现高效的大模型产业级应用。 Easy-to-use and powerful LLM and SLM library with awesome model zoo.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
项目展示
查看全部项目 >- 暂无简介Star
- 飞桨多语言OCR工具包（实用超轻量OCR系统，支持80+种语言识别，提供数据标注与合成工具，支持服务器、移动端、嵌入式及IoT设备端的训练与部署） Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)Star
- 暂无简介like
- like
- like
- like
- PaddleOCR-VL-1.5 是 PaddleOCR-VL 的新一代进阶模型，在 OmniDocBench v1.5 上实现了 94.5% 的全新 state-of-the-art 准确率。 为了严格评估模型在真实物理畸变下的鲁棒性——包括扫描伪影、倾斜、扭曲、屏幕拍摄和光照变化——我们提出了 Real5-OmniDocBench 基准测试集。实验结果表明，该增强模型在新构建的基准测试集上达到了 SOTA 性能。此外，我们通过整合印章识别和文本检测识别（text spotting）任务扩展了模型的能力，同时保持 0.9B 的超紧凑 VLM 规模，具备高效率特性。like
- like
- like
- like