Browse Source

update for 3.1 (#4290)

cuicheng01 4 tháng trước cách đây
mục cha
commit
017ea028de
5 tập tin đã thay đổi với 35 bổ sung1 xóa
  1. 9 0
      README.md
  2. 9 0
      README_en.md
  3. 8 0
      docs/CHANGELOG.en.md
  4. 8 0
      docs/CHANGELOG.md
  5. 1 1
      paddlex/.version

+ 9 - 0
README.md

@@ -35,6 +35,15 @@ PaddleX 3.0 是基于飞桨框架构建的低代码开发工具,它集成了
 
 ## 📣 近期更新
 
+🔥🔥 **2025.6.28,发布 PaddleX v3.1.0**,新增能力如下:
+
+- **重要模型:**
+  - **新增PP-OCRv5多语种文本识别模型**,支持法语、西班牙语、葡萄牙语、俄语、韩语等37种语言的文字识别模型的训推流程。**平均精度涨幅超30%。**
+  - 升级PP-StructureV3中的**PP-Chart2Table模型**,图表转表能力进一步升级,在内部自建测评集合上指标(RMS-F1)**提升9.36个百分点(71.24% -> 80.60%)**
+- **重要产线:**
+  - 新增基于PP-StructureV3和ERNIE 4.5 Turbo的**文档翻译产线PP-DocTranslation,支持翻译Markdown文档、各种复杂版式的PDF文档和文档图像,结果保存为Markdown格式文档。**
+
+
 🔥🔥 **2025.5.20,发布 PaddleX v3.0.0**,相比PaddleX v2.x,核心升级如下:
 
 **丰富的模型库:**

+ 9 - 0
README_en.md

@@ -38,6 +38,15 @@ PaddleX 3.0 is a low-code development tool for AI models built on the PaddlePadd
 ## 📣 Recent Updates
 
 
+🔥🔥 **2025.6.28, PaddleX v3.1.0 Released**
+
+- **Key Models:**
+  - **Added PP-OCRv5 Multilingual Text Recognition Model**, supporting training and inference workflows for text recognition in 37 languages, including French, Spanish, Portuguese, Russian, Korean, and more. **Average precision increased by over 30%.**
+  - Upgraded **PP-Chart2Table model in PP-StructureV3**. Chart-to-table conversion capability further improved, with RMS-F1 on our internal evaluation set **increased by 9.36 percentage points (71.24% -> 80.60%)**.
+- **Key Pipelines:**
+  - Added **document translation pipeline PP-DocTranslation** based on PP-StructureV3 and ERNIE 4.5 Turbo. Supports translation of Markdown documents, various complex-layout PDF documents, and document images, with results saved as Markdown format documents.
+
+
 🔥🔥 **2025.5.20: PaddleX v3.0.0 Released**
 
 Core upgrades are as follows:

+ 8 - 0
docs/CHANGELOG.en.md

@@ -6,6 +6,14 @@ comments: true
 
 ## Latest Version Information
 
+### PaddleX v3.1.0(6.28/2025)
+
+- **Key Models:**
+  - **Added PP-OCRv5 Multilingual Text Recognition Model**, supporting training and inference workflows for text recognition in 37 languages, including French, Spanish, Portuguese, Russian, Korean, and more. **Average precision increased by over 30%.**
+  - Upgraded **PP-Chart2Table model in PP-StructureV3**. Chart-to-table conversion capability further improved, with RMS-F1 on our internal evaluation set **increased by 9.36 percentage points (71.24% -> 80.60%)**.
+- **Key Pipelines:**
+  - Added **document translation pipeline PP-DocTranslation** based on PP-StructureV3 and ERNIE 4.5 Turbo. Supports translation of Markdown documents, various complex-layout PDF documents, and document images, with results saved as Markdown format documents.
+
 ### PaddleX v3.0.0(5.20/2025)
 
 Core upgrades are as follows:

+ 8 - 0
docs/CHANGELOG.md

@@ -6,6 +6,14 @@ comments: true
 
 ## 最新版本信息
 
+### PaddleX v3.1.0(6.28/2025)
+
+- **重要模型:**
+  - **新增PP-OCRv5多语种文本识别模型**,支持法语、西班牙语、葡萄牙语、俄语、韩语等37种语言的文字识别模型的训推流程。**平均精度涨幅超30%。**
+  - 升级PP-StructureV3中的**PP-Chart2Table模型**,图表转表能力进一步升级,在内部自建测评集合上指标(RMS-F1)**提升9.36个百分点(71.24% -> 80.60%)**
+- **重要产线:**
+  - 新增基于PP-StructureV3和ERNIE 4.5 Turbo的**文档翻译产线PP-DocTranslation,支持翻译Markdown文档、各种复杂版式的PDF文档和文档图像,结果保存为Markdown格式文档。**
+
 
 ### PaddleX v3.0.0(5.20/2025)
 

+ 1 - 1
paddlex/.version

@@ -1 +1 @@
-3.0.3
+3.1.0