Merge pull request #1465 from opendatalab/dev

Dev

README.md

@@ -42,13 +42,15 @@
 </div>
 
 # Changelog
-- 2025/01/06 1.0.0 released. This is our first official release, where we have introduced a completely new API interface and enhanced compatibility through extensive refactoring:
+- 2025/01/06 1.0.0 released. This is our first official release, where we have introduced a completely new API interface and enhanced compatibility through extensive refactoring, as well as a brand new automatic language identification feature:
   - New API Interface
     - For the data-side API, we have introduced the Dataset class, designed to provide a robust and flexible data processing framework. This framework currently supports a variety of document formats, including images (.jpg and .png), PDFs, Word documents (.doc and .docx), and PowerPoint presentations (.ppt and .pptx). It ensures effective support for data processing tasks ranging from simple to complex.
     - For the user-side API, we have meticulously designed the MinerU processing workflow as a series of composable Stages. Each Stage represents a specific processing step, allowing users to define new Stages according to their needs and creatively combine these stages to customize their data processing workflows.
   - Enhanced Compatibility
     - By optimizing the dependency environment and configuration items, we ensure stable and efficient operation on ARM architecture Linux systems.
-    - We have deeply integrated with Huawei Ascend NPU acceleration, providing autonomous and controllable high-performance computing capabilities. This supports the localization and development of AI application platforms in China.
+    - We have deeply integrated with Huawei Ascend NPU acceleration, providing autonomous and controllable high-performance computing capabilities. This supports the localization and development of AI application platforms in China. [Ascend NPU Acceleration](docs/README_Ascend_NPU_Acceleration_zh_CN.md)
+  - Automatic Language Identification
+    - By introducing a new language recognition model, setting the `lang` configuration to `auto` during document parsing will automatically select the appropriate OCR language model, improving the accuracy of scanned document parsing.
 - 2024/11/22 0.10.0 released. Introducing hybrid OCR text extraction capabilities,
   - Significantly improved parsing performance in complex text distribution scenarios such as dense formulas, irregular span regions, and text represented by images.
   - Combines the dual advantages of accurate content extraction and faster speed in text mode, and more precise span/line region recognition in OCR mode.

README_zh-CN.md

@@ -42,13 +42,15 @@
 </div>
 
 # 更新记录
-- 2025/01/06 1.0.0 发布，这是我们的第一个正式版本，在这个版本中，我们通过大量重构带来了全新的API接口和更广泛的兼容性：
+- 2025/01/06 1.0.0 发布，这是我们的第一个正式版本，在这个版本中，我们通过大量重构带来了全新的API接口和更广泛的兼容性，以及全新的自动语言识别功能：
   - 全新API接口 
     - 对于数据侧API，我们引入了Dataset类，旨在提供一个强大而灵活的数据处理框架。该框架当前支持包括图像（.jpg及.png）、PDF、Word（.doc及.docx）、以及PowerPoint（.ppt及.pptx）在内的多种文档格式，确保了从简单到复杂的数据处理任务都能得到有效的支持。
     - 针对用户侧API，我们将MinerU的处理流程精心设计为一系列可组合的Stage阶段。每个Stage代表了一个特定的处理步骤，用户可以根据自身需求自由地定义新的Stage，并通过创造性地组合这些阶段来定制专属的数据处理流程。
   - 更广泛的兼容性适配
     - 通过优化依赖环境和配置项，确保在ARM架构的Linux系统上能够稳定高效运行。
-    - 深度适配华为昇腾NPU加速，积极响应信创要求，提供自主可控的高性能计算能力，助力人工智能应用平台的国产化应用与发展。
+    - 深度适配华为昇腾NPU加速，积极响应信创要求，提供自主可控的高性能计算能力，助力人工智能应用平台的国产化应用与发展。[NPU加速教程](docs/README_Ascend_NPU_Acceleration_zh_CN.md)
+  - 自动语言识别
+    - 通过引入全新的语言识别模型， 在文档解析中将`lang`配置为`auto`，即可自动选择合适的OCR语言模型，提升扫描类文档解析的准确性。
 - 2024/11/22 0.10.0发布，通过引入混合OCR文本提取能力，
   - 在公式密集、span区域不规范、部分文本使用图像表现等复杂文本分布场景下获得解析效果的显著提升
   - 同时具备文本模式内容提取准确、速度更快与OCR模式span/line区域识别更准的双重优势

magic_pdf/model/sub_modules/table/rapidtable/rapid_table.py

@@ -8,17 +8,25 @@ from rapid_table import RapidTable
 class RapidTableModel(object):
     def __init__(self, ocr_engine):
         self.table_model = RapidTable()
-        if ocr_engine is None:
-            self.ocr_model_name = "RapidOCR"
-            if torch.cuda.is_available():
-                from rapidocr_paddle import RapidOCR
-                self.ocr_engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True)
-            else:
-                from rapidocr_onnxruntime import RapidOCR
-                self.ocr_engine = RapidOCR()
+        # if ocr_engine is None:
+        #     self.ocr_model_name = "RapidOCR"
+        #     if torch.cuda.is_available():
+        #         from rapidocr_paddle import RapidOCR
+        #         self.ocr_engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True)
+        #     else:
+        #         from rapidocr_onnxruntime import RapidOCR
+        #         self.ocr_engine = RapidOCR()
+        # else:
+        #     self.ocr_model_name = "PaddleOCR"
+        #     self.ocr_engine = ocr_engine
+
+        self.ocr_model_name = "RapidOCR"
+        if torch.cuda.is_available():
+            from rapidocr_paddle import RapidOCR
+            self.ocr_engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True)
         else:
-            self.ocr_model_name = "PaddleOCR"
-            self.ocr_engine = ocr_engine
+            from rapidocr_onnxruntime import RapidOCR
+            self.ocr_engine = RapidOCR()
 
     def predict(self, image):
 

projects/gradio_app/app.py

@@ -193,7 +193,7 @@ if __name__ == '__main__':
                 max_pages = gr.Slider(1, 20, 10, step=1, label='Max convert pages')
                 with gr.Row():
                     layout_mode = gr.Dropdown(['layoutlmv3', 'doclayout_yolo'], label='Layout model', value='doclayout_yolo')
-                    language = gr.Dropdown(all_lang, label='Language', value='')
+                    language = gr.Dropdown(all_lang, label='Language', value='auto')
                 with gr.Row():
                     formula_enable = gr.Checkbox(label='Enable formula recognition', value=True)
                     is_ocr = gr.Checkbox(label='Force enable OCR', value=False)
@@ -221,6 +221,6 @@ if __name__ == '__main__':
         file.change(fn=to_pdf, inputs=file, outputs=pdf_show)
         change_bu.click(fn=to_markdown, inputs=[file, max_pages, is_ocr, layout_mode, formula_enable, table_enable, language],
                         outputs=[md, md_text, output_file, pdf_show])
-        clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr, language])
+        clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr])
 
     demo.launch(server_name='0.0.0.0')

requirements.txt

 boto3>=1.28.43
 Brotli>=1.1.0
 click>=8.1.7
-fast-langdetect==0.2.0
+fast-langdetect>=0.2.3
 loguru>=0.6.0
 numpy>=1.21.6,<2.0.0
 pydantic>=2.7.2