Skip to content

Commit 017ea02

Browse files
authored
update for 3.1 (#4290)
1 parent 9d77cac commit 017ea02

File tree

5 files changed

+35
-1
lines changed

5 files changed

+35
-1
lines changed

README.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -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
3535

3636
## 📣 近期更新
3737

38+
🔥🔥 **2025.6.28,发布 PaddleX v3.1.0**,新增能力如下:
39+
40+
- **重要模型:**
41+
- **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%。**
42+
- 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%)**
43+
- **重要产线:**
44+
- 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。**
45+
46+
3847
🔥🔥 **2025.5.20,发布 PaddleX v3.0.0**,相比PaddleX v2.x,核心升级如下:
3948

4049
**丰富的模型库:**

README_en.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -38,6 +38,15 @@ PaddleX 3.0 is a low-code development tool for AI models built on the PaddlePadd
3838
## 📣 Recent Updates
3939

4040

41+
🔥🔥 **2025.6.28, PaddleX v3.1.0 Released**
42+
43+
- **Key Models:**
44+
- **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%.**
45+
- 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%)**.
46+
- **Key Pipelines:**
47+
- 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.
48+
49+
4150
🔥🔥 **2025.5.20: PaddleX v3.0.0 Released**
4251

4352
Core upgrades are as follows:

docs/CHANGELOG.en.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,14 @@ comments: true
66

77
## Latest Version Information
88

9+
### PaddleX v3.1.0(6.28/2025)
10+
11+
- **Key Models:**
12+
- **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%.**
13+
- 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%)**.
14+
- **Key Pipelines:**
15+
- 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.
16+
917
### PaddleX v3.0.0(5.20/2025)
1018

1119
Core upgrades are as follows:

docs/CHANGELOG.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,14 @@ comments: true
66

77
## 最新版本信息
88

9+
### PaddleX v3.1.0(6.28/2025)
10+
11+
- **重要模型:**
12+
- **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%。**
13+
- 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%)**
14+
- **重要产线:**
15+
- 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。**
16+
917

1018
### PaddleX v3.0.0(5.20/2025)
1119

paddlex/.version

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
3.0.3
1+
3.1.0

0 commit comments

Comments
 (0)