[Docs] Docs/update docs2 (#2266)

* update service_deploy.md & EN.md

* add General Seal Text Detection Pipeline in high_preformance_inference.md and EN.md

* change "keys = XXX" in document_scene_information_extraction_en.md

* pull newest branch and fix the problems above.

* Update service_deploy.md

* Update service_deploy_en.md

* Fix pipeline Chinese names

---------

Co-authored-by: Lin Manhui <mhlin425@whu.edu.cn>
Co-authored-by: Bobholamovic <bob1998425@hotmail.com>

README.md

@@ -20,7 +20,7 @@
 
 ## 🔍 简介
 
-PaddleX 3.0 是基于飞桨框架构建的低代码开发工具，它集成了众多**开箱即用的预训练模型**，可以实现模型从训练到推理的**全流程开发**，支持国内外**多款主流硬件**，助力AI 开发者进行产业实践。  
+PaddleX 3.0 是基于飞桨框架构建的低代码开发工具，它集成了众多**开箱即用的预训练模型**，可以实现模型从训练到推理的**全流程开发**，支持国内外**多款主流硬件**，助力AI 开发者进行产业实践。
 
 |                                                            [**通用图像分类**](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md)                                                            |                                                            [**图像多标签分类**](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md)                                                            |                                                            [**通用目标检测**](./docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md)                                                            |                                                            [**通用实例分割**](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md)                                                            |
 |:--------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------:|
@@ -33,7 +33,7 @@ PaddleX 3.0 是基于飞桨框架构建的低代码开发工具，它集成了
 ## 🌟 特性
   🎨 **模型丰富一键调用**：将覆盖文本图像智能分析、OCR、目标检测、时序预测等多个关键领域的 **200+ 飞桨模型**整合为 **19 条模型产线**，通过极简的 Python API 一键调用，快速体验模型效果。同时支持 **20+ 单功能模块**，方便开发者进行模型组合使用。
 
-  🚀 **提高效率降低门槛**：实现基于统一命令和图形界面的模型**全流程开发**，打造大小模型结合、大模型半监督学习和多模型融合的[**8 条特色模型产线**](https://aistudio.baidu.com/intro/paddlex)，大幅度降低迭代模型的成本。  
+  🚀 **提高效率降低门槛**：实现基于统一命令和图形界面的模型**全流程开发**，打造大小模型结合、大模型半监督学习和多模型融合的[**8 条特色模型产线**](https://aistudio.baidu.com/intro/paddlex)，大幅度降低迭代模型的成本。
 
   🌐 **多种场景灵活部署**：支持**高性能部署**、**服务化部署**和**端侧部署**等多种部署方式，确保不同应用场景下模型的高效运行和快速响应。
 
@@ -224,7 +224,7 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持**在
         <td>🚧</td>
     </tr>
     <tr>
-        <td>印章识别</td>
+        <td>印章文本识别</td>
         <td>🚧</td>
         <td>✅</td>
         <td>✅</td>
@@ -274,7 +274,7 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持**在
         <td>🚧</td>
     </tr>
 
-    
+
 </table>
 
 > ❗注：以上功能均基于 GPU/CPU 实现。PaddleX 还可在昆仑芯、昇腾、寒武纪和海光等主流硬件上进行快速推理和二次开发。下表详细列出了模型产线的支持情况，具体支持的模型列表请参阅[模型列表(昆仑芯XPU)](./docs/support_list/model_list_xpu.md)/[模型列表(昇腾NPU)](./docs/support_list/model_list_npu.md)/[模型列表(寒武纪MLU)](./docs/support_list/model_list_mlu.md)/[模型列表(海光DCU)](./docs/support_list/model_list_dcu.md)。我们正在适配更多的模型，并在主流硬件上推动高性能和服务化部署的实施。
@@ -379,7 +379,7 @@ python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.
 ```bash
 pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0b1-py3-none-any.whl
 ```
-  
+
 > ❗ 更多安装方式参考 [PaddleX 安装教程](./docs/installation/installation.md)
 
 ### 💻 命令行使用
@@ -405,7 +405,7 @@ paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddle
 
 ```bash
 {
-'input_path': '/root/.paddlex/predict_input/general_ocr_002.png', 
+'input_path': '/root/.paddlex/predict_input/general_ocr_002.png',
 'dt_polys': [array([[161,  27],
        [353,  22],
        [354,  69],
@@ -419,9 +419,9 @@ paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddle
        [405, 106],
        [405, 128],
        [341, 128]], dtype=int16)
-       ...], 
-'dt_scores': [0.758478200014338, 0.7021546472698513, 0.8536622648391111, 0.8619181462164781, 0.8321051217096188, 0.8868756173427551, 0.7982964727675609, 0.8289939036796322, 0.8289428877522524, 0.8587063317632897, 0.7786755892491615, 0.8502032769081344, 0.8703346500042997, 0.834490931790065, 0.908291103353393, 0.7614978661708064, 0.8325774055997542, 0.7843421347676149, 0.8680889482955594, 0.8788859304537682, 0.8963341277518075, 0.9364654810069546, 0.8092413027028257, 0.8503743089091863, 0.7920740420391101, 0.7592224394793805, 0.7920547400069311, 0.6641757962457888, 0.8650289477605955, 0.8079483304467047, 0.8532207681055275, 0.8913377034754717], 
-'rec_text': ['登机牌', 'BOARDING', 'PASS', '舱位', 'CLASS', '序号 SERIALNO.', '座位号', '日期 DATE', 'SEAT NO', '航班 FLIGHW', '035', 'MU2379', '始发地', 'FROM', '登机口', 'GATE', '登机时间BDT', '目的地TO', '福州', 'TAIYUAN', 'G11', 'FUZHOU', '身份识别IDNO', '姓名NAME', 'ZHANGQIWEI', 票号TKTNO', '张祺伟', '票价FARE', 'ETKT7813699238489/1', '登机口于起飞前10分钟关闭GATESCLOSE10MINUTESBEFOREDEPARTURETIME'], 
+       ...],
+'dt_scores': [0.758478200014338, 0.7021546472698513, 0.8536622648391111, 0.8619181462164781, 0.8321051217096188, 0.8868756173427551, 0.7982964727675609, 0.8289939036796322, 0.8289428877522524, 0.8587063317632897, 0.7786755892491615, 0.8502032769081344, 0.8703346500042997, 0.834490931790065, 0.908291103353393, 0.7614978661708064, 0.8325774055997542, 0.7843421347676149, 0.8680889482955594, 0.8788859304537682, 0.8963341277518075, 0.9364654810069546, 0.8092413027028257, 0.8503743089091863, 0.7920740420391101, 0.7592224394793805, 0.7920547400069311, 0.6641757962457888, 0.8650289477605955, 0.8079483304467047, 0.8532207681055275, 0.8913377034754717],
+'rec_text': ['登机牌', 'BOARDING', 'PASS', '舱位', 'CLASS', '序号 SERIALNO.', '座位号', '日期 DATE', 'SEAT NO', '航班 FLIGHW', '035', 'MU2379', '始发地', 'FROM', '登机口', 'GATE', '登机时间BDT', '目的地TO', '福州', 'TAIYUAN', 'G11', 'FUZHOU', '身份识别IDNO', '姓名NAME', 'ZHANGQIWEI', 票号TKTNO', '张祺伟', '票价FARE', 'ETKT7813699238489/1', '登机口于起飞前10分钟关闭GATESCLOSE10MINUTESBEFOREDEPARTURETIME'],
 'rec_score': [0.9985831379890442, 0.999696917533874512, 0.9985735416412354, 0.9842517971992493, 0.9383274912834167, 0.9943678975105286, 0.9419361352920532, 0.9221674799919128, 0.9555020928382874, 0.9870321154594421, 0.9664073586463928, 0.9988052248954773, 0.9979352355003357, 0.9985110759735107, 0.9943482875823975, 0.9991195797920227, 0.9936401844024658, 0.9974591135978699, 0.9743705987930298, 0.9980487823486328, 0.9874696135520935, 0.9900962710380554, 0.9952947497367859, 0.9950481653213501, 0.989926815032959, 0.9915552139282227, 0.9938777685165405, 0.997239887714386, 0.9963340759277344, 0.9936134815216064, 0.97223961353302]}
 ```
 
@@ -449,7 +449,7 @@ paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddle
 | 通用表格识别       | `paddlex --pipeline table_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg --device gpu:0`                                      |
 | 通用版面解析       | `paddlex --pipeline layout_parsing --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/demo_paper.png --device gpu:0`                                      |
 | 公式识别       | `paddlex --pipeline formula_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/demo_image/general_formula_recognition.png --device gpu:0`                                      |
-| 印章识别       | `paddlex --pipeline seal_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/seal_text_det.png --device gpu:0`                                      |
+| 印章文本识别       | `paddlex --pipeline seal_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/seal_text_det.png --device gpu:0`                                      |
 | 时序预测       | `paddlex --pipeline ts_fc --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_fc.csv --device gpu:0`                                                                   |
 | 时序异常检测   | `paddlex --pipeline ts_ad --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_ad.csv --device gpu:0`                                                                    |
 | 时序分类       | `paddlex --pipeline ts_cls --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_cls.csv --device gpu:0`                                                                 |
@@ -493,7 +493,7 @@ for res in output:
 | 通用表格识别       | `table_recognition`                | [通用表格识别产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md#22-python脚本方式集成)                                   |
 | 通用版面解析       | `layout_parsing`                | [通用版面解析产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md#22-python脚本方式集成)                                   |
 | 公式识别       | `formula_recognition`                | [公式识别产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md#22-python脚本方式集成)                                   |
-| 印章识别       | `seal_recognition`                | [印章识别产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md#22-python脚本方式集成)                                   |
+| 印章文本识别       | `seal_recognition`                | [印章文本识别产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md#22-python脚本方式集成)                                   |
 | 时序预测       | `ts_fc`                            | [通用时序预测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md#222-python脚本方式集成)                    |
 | 时序异常检测   | `ts_ad`                            | [通用时序异常检测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md#222-python脚本方式集成)          |
 | 时序分类       | `ts_cls`                           | [通用时序分类产线Python脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md#222-python脚本方式集成)                 |
@@ -504,9 +504,9 @@ for res in output:
 ## 📖 文档
 <details>
   <summary> <b> ⬇️ 安装 </b></summary>
-  
+
   * [📦 PaddlePaddle 安装教程](./docs/installation/paddlepaddle_install.md)
-  * [📦 PaddleX 安装教程](./docs/installation/installation.md) 
+  * [📦 PaddleX 安装教程](./docs/installation/installation.md)
 
 
 </details>
@@ -529,7 +529,7 @@ for res in output:
     * [📊 通用表格识别产线使用教程](./docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md)
     * [📄 通用版面解析产线使用教程](./docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md)
     * [📐 公式识别产线使用教程](./docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md)
-    * [📝 印章识别产线使用教程](./docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md)
+    * [📝 印章文本识别产线使用教程](./docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md)
   </details>
 
 * <details open>
@@ -542,7 +542,7 @@ for res in output:
    * [🏷️ 图像多标签分类产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md)
    * [🔍 小目标检测产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md)
    * [🖼️ 图像异常检测产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md)
-  
+
 
 * <details open>
     <summary> <b> ⏱️ 时序分析</b> </summary>
@@ -560,7 +560,7 @@ for res in output:
    * [🖥️ PaddleX 产线命令行使用说明](./docs/pipeline_usage/instructions/pipeline_CLI_usage.md)
    * [📝 PaddleX 产线 Python 脚本使用说明](./docs/pipeline_usage/instructions/pipeline_python_API.md)
   </details>
-   
+
 </details>
 
 <details open>
@@ -577,7 +577,7 @@ for res in output:
   * [📄 文档图像方向分类使用教程](./docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md)
   * [🔧 文本图像矫正模块使用教程](./docs/module_usage/tutorials/ocr_modules/text_image_unwarping.md)
   * [📐 公式识别模块使用教程](./docs/module_usage/tutorials/ocr_modules/formula_recognition.md)
-  
+
   </details>
 
 * <details open>
@@ -623,7 +623,7 @@ for res in output:
   * [🚨 时序异常检测模块使用教程](./docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md)
   * [🕒 时序分类模块使用教程](./docs/module_usage/tutorials/time_series_modules/time_series_classification.md)
   </details>
-    
+
 * <details>
   <summary> <b> 📄 相关说明文件 </b></summary>
 
@@ -644,7 +644,7 @@ for res in output:
 </details>
 <details open>
   <summary> <b> 🖥️ 多硬件使用 </b></summary>
-  
+
   * [🔧 多硬件使用指南](./docs/other_devices_support/multi_devices_use_guide.md)
   * [🖲️ 海光 DCU 飞桨安装教程](./docs/other_devices_support/paddlepaddle_install_DCU.md)
   * [🔲 寒武纪 MLU 飞桨安装教程](./docs/other_devices_support/paddlepaddle_install_MLU.md)
@@ -680,4 +680,3 @@ for res in output:
 ## 📄 许可证书
 
 本项目的发布受 [Apache 2.0 license](./LICENSE) 许可认证。
-

docs/pipeline_deploy/high_performance_inference.md

@@ -190,6 +190,23 @@ PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在
   </tr>
 
   <tr>
+    <td rowspan="3">印章文本识别</td>
+    <td>版面区域分析</td>
+    <td>PicoDet-L_layout_3cls<br/>RT-DETR-H_layout_3cls<br/>RT-DETR-H_layout_17cls</td>
+  </tr>
+
+  <tr>
+    <td>印章文本检测</td>
+    <td>PP-OCRv4_server_seal_det<br/>PP-OCRv4_mobile_seal_det</td>
+  </tr>
+
+  <tr>
+    <td>文本识别</td>
+    <td>PP-OCRv4_mobile_rec<br/>PP-OCRv4_server_rec</td>
+  </tr>
+  
+
+  <tr>
     <td rowspan="5">通用表格识别</td>
     <td>版面区域检测</td>
     <td>PicoDet_layout_1x</td>

docs/pipeline_deploy/high_performance_inference_en.md

@@ -181,6 +181,22 @@ PaddleX provides default high-performance inference configurations for each mode
   </tr>
 
   <tr>
+    <td rowspan="3">Seal Text Recognition</td>
+    <td>Layout Analysis</td>
+    <td>PicoDet-L_layout_3cls<br/>RT-DETR-H_layout_3cls<br/>RT-DETR-H_layout_17cls</td>
+  </tr>
+
+  <tr>
+    <td>Seal Text Detection</td>
+    <td>PP-OCRv4_server_seal_det<br/>PP-OCRv4_mobile_seal_det</td>
+  </tr>
+
+  <tr>
+    <td>Text Recognition</td>
+    <td>PP-OCRv4_mobile_rec<br/>PP-OCRv4_server_rec</td>
+  </tr>
+
+  <tr>
     <td rowspan="2">General OCR</td>
     <td>Text Detection</td>
     <td>PP-OCRv4_server_det<br/>PP-OCRv4_mobile_det</td>

docs/pipeline_deploy/service_deploy.md

@@ -74,6 +74,9 @@ INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
 | 图像异常检测产线       | [图像异常检测产线使用教程](../pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md)       |
 | 通用OCR产线            | [通用OCR产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/OCR.md)            |
 | 通用表格识别产线       | [通用表格识别产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/table_recognition.md)       |
+| 通用版面解析产线       | [通用版面解析产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md)       |
+| 公式识别产线       | [公式识别产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md)       |
+| 印章文本识别产线       | [印章文本识别产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md)       |
 | 时序预测产线           | [时序预测产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md)           |
 | 时序异常检测产线       | [时序异常检测产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md)       |
 | 时序分类产线           | [时序分类产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md)           |

docs/pipeline_deploy/service_deploy_en.md

@@ -75,6 +75,9 @@ Please refer to the **"Development Integration/Deployment"** section in the usag
 | Image Anomaly Detection Pipeline | [Tutorial for Using the Image Anomaly Detection Pipeline](../pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md) |
 | General OCR Pipeline | [Tutorial for Using the General OCR Pipeline](../pipeline_usage/tutorials/ocr_pipelines/OCR_en.md) |
 | General Table Recognition Pipeline | [Tutorial for Using the General Table Recognition Pipeline](../pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md) |
+| General Layout Parsing Pipeline | [Tutorial for Using the Layout Parsing Recognition Pipeline](../pipeline_usage/tutorials/ocr_pipelines/layout_parsing_en.md) |
+| Formula Recognition Pipeline | [Tutorial for Using the Formula Recognition Pipeline](../pipeline_usage/tutorials/ocr_pipelines/formula_recognition_en.md) |
+| Seal Text Recognition Pipeline | [Tutorial for Using the Seal Text Recognition Pipeline](../pipeline_usage/tutorials/ocr_pipelines/seal_recognition_en.md) |
 | Time Series Forecasting Pipeline | [Tutorial for Using the Time Series Forecasting Pipeline](../pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md) |
 | Time Series Anomaly Detection Pipeline | [Tutorial for Using the Time Series Anomaly Detection Pipeline](../pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md) |
 | Time Series Classification Pipeline | [Tutorial for Using the Time Series Classification Pipeline](../pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md) |

docs/pipeline_usage/pipeline_develop_guide.md

@@ -43,7 +43,7 @@ PaddleX提供了三种可以快速体验产线效果的方式，您可以根据
 以实现登机牌识别任务的通用OCR产线为例，可以用三种方式体验产线效果：
 
 **🌐 在线体验**
-  
+
 您可以在AI Studio[在线体验](https://aistudio.baidu.com/community/app/91660/webUI?source=appMineRecent)通用 OCR 产线的效果，用官方提供的 Demo 图片进行识别，例如：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/ocr/02.png)
@@ -88,7 +88,7 @@ paddlex --pipeline OCR --input general_ocr_002.png --device gpu:0
 <details>
    <summary> 👉点击展开</summary>
 
-获取OCR产线配置文件：   
+获取OCR产线配置文件：
 ```bash
 paddlex --get_pipeline_config OCR
 ```
@@ -205,8 +205,7 @@ Pipeline:
 | 通用表格识别       | [通用表格识别产线使用教程](./tutorials/ocr_pipelines/table_recognition.md) |
 | 通用版面解析       | [通用版面解析产线使用教程](./tutorials/ocr_pipelines/layout_parsing.md) |
 | 公式识别       | [公式识别产线使用教程](./tutorials/ocr_pipelines/formula_recognition.md) |
-| 印章识别       | [印章识别产线使用教程](./tutorials/ocr_pipelines/seal_recognition.md) |
+| 印章文本识别       | [印章文本识别产线使用教程](./tutorials/ocr_pipelines/seal_recognition.md) |
 | 时序预测       | [通用时序预测产线使用教程](./tutorials/time_series_pipelines/time_series_forecasting.md) |
 | 时序异常检测   | [通用时序异常检测产线使用教程](./tutorials/time_series_pipelines/time_series_anomaly_detection.md) |
 | 时序分类       | [通用时序分类产线使用教程](./tutorials/time_series_pipelines/time_series_classification.md) |
-

docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md

@@ -558,7 +558,7 @@ LLM_PARAMS = {
 }
 
 file_path = "./demo.jpg"
-keys = ["phone number"]
+keys = ["电话"]
 
 with open(file_path, "rb") as file:
     file_bytes = file.read()

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -1,8 +1,8 @@
 简体中文 | [English](formula_recognition_en.md)
 
-# 通用公式识别产线使用教程
+# 公式识别产线使用教程
 
-## 1. 通用公式识别产线介绍
+## 1. 公式识别产线介绍
 
 公式识别是一种自动从文档或图像中识别和提取LaTeX公式内容及其结构的技术，广泛应用于数学、物理、计算机科学等领域的文档编辑和数据分析。通过使用计算机视觉和机器学习算法，公式识别能够将复杂的数学公式信息转换为可编辑的LaTeX格式，方便用户进一步处理和分析数据。
 
@@ -109,7 +109,7 @@ paddlex --pipeline ./formula_recognition.yaml --input general_formula_recognitio
 可视化图片默认不进行保存，您可以通过 `--save_path` 自定义保存路径，随后所有结果将被保存在指定路径下。此外，您可以通过网站 [https://www.lddgo.net/math/latex-to-image](https://www.lddgo.net/math/latex-to-image) 对识别出来的LaTeX代码进行可视化。
 
 ### 2.2 Python脚本方式集成
-几行代码即可完成产线的快速推理，以通用公式识别产线为例：
+几行代码即可完成产线的快速推理，以公式识别产线为例：
 
 ```python
 from paddlex import create_pipeline
@@ -126,7 +126,7 @@ for res in output:
 
 在上述 Python 脚本中，执行了如下几个步骤：
 
-（1）实例化 `create_pipeline` 实例化 通用公式识别产线对象：具体参数说明如下：
+（1）实例化 `create_pipeline` 实例化 公式识别产线对象：具体参数说明如下：
 
 |参数|参数说明|参数类型|默认值|
 |-|-|-|-|
@@ -134,7 +134,7 @@ for res in output:
 |`device`|产线模型推理设备。支持：“gpu”，“cpu”。|`str`|`gpu`|
 |`use_hpip`|是否启用高性能推理，仅当该产线支持高性能推理时可用。|`bool`|`False`|
 
-（2）调用通用公式识别产线对象的 `predict` 方法进行推理预测：`predict` 方法参数为`x`，用于输入待预测数据，支持多种输入方式，具体示例如下：
+（2）调用公式识别产线对象的 `predict` 方法进行推理预测：`predict` 方法参数为`x`，用于输入待预测数据，支持多种输入方式，具体示例如下：
 
 | 参数类型      | 参数说明                                                                                                  |
 |---------------|-----------------------------------------------------------------------------------------------------------|
@@ -155,7 +155,7 @@ for res in output:
 | save_to_json | 将结果保存为json格式的文件   | `- save_path`：str类型，保存的文件路径，当为目录时，保存文件命名与输入文件类型命名一致；<br>`- indent`：int类型，json格式化设置，默认为4；<br>`- ensure_ascii`：bool类型，json格式化设置，默认为False； |
 | save_to_img  | 将结果保存为图像格式的文件  | `- save_path`：str类型，保存的文件路径，当为目录时，保存文件命名与输入文件类型命名一致； |
 
-若您获取了配置文件，即可对通用公式识别产线各项配置进行自定义，只需要修改 `create_pipeline` 方法中的 `pipeline` 参数值为产线配置文件路径即可。
+若您获取了配置文件，即可对公式识别产线各项配置进行自定义，只需要修改 `create_pipeline` 方法中的 `pipeline` 参数值为产线配置文件路径即可。
 
 例如，若您的配置文件保存在 `./my_path/formula_recognition.yaml` ，则只需执行：
 
@@ -168,9 +168,9 @@ for res in output:
     res.save_to_img("./output/")
 ```
 ## 3. 开发集成/部署
-如果通用公式识别产线可以达到您对产线推理速度和精度的要求，您可以直接进行开发集成/部署。
+如果公式识别产线可以达到您对产线推理速度和精度的要求，您可以直接进行开发集成/部署。
 
-若您需要将通用公式识别产线直接应用在您的Python项目中，可以参考 [2.2 Python脚本方式](#22-python脚本方式集成)中的示例代码。
+若您需要将公式识别产线直接应用在您的Python项目中，可以参考 [2.2 Python脚本方式](#22-python脚本方式集成)中的示例代码。
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
@@ -665,10 +665,10 @@ print_r($result["formulas"]);
 
 
 ## 4. 二次开发
-如果通用公式识别产线提供的默认模型权重在您的场景中，精度或速度不满意，您可以尝试利用**您自己拥有的特定领域或应用场景的数据**对现有模型进行进一步的**微调**，以提升通用公式识别产线的在您的场景中的识别效果。
+如果公式识别产线提供的默认模型权重在您的场景中，精度或速度不满意，您可以尝试利用**您自己拥有的特定领域或应用场景的数据**对现有模型进行进一步的**微调**，以提升公式识别产线的在您的场景中的识别效果。
 
 ### 4.1 模型微调
-由于通用通用公式识别产线包含两个模块（版面区域检测模块和公式识别），模型产线的效果不及预期可能来自于其中任何一个模块。
+由于公式识别产线包含两个模块（版面区域检测模块和公式识别），模型产线的效果不及预期可能来自于其中任何一个模块。
 
 您可以对识别效果差的图片进行分析，如果在分析过程中发现有较多的公式未被检测出来（即公式漏检现象），那么可能是版面区域检测模型存在不足，您需要参考[版面区域检测模块开发教程](../../../module_usage/tutorials/ocr_modules/layout_detection.md)中的[二次开发](../../../module_usage/tutorials/ocr_modules/layout_detection.md#四二次开发)章节，使用您的私有数据集对版面区域检测模型进行微调；如果在已检测到的公式中出现较多的识别错误（即识别出的公式内容与实际公式内容不符），这表明公式识别模型需要进一步改进，您需要参考[公式识别模块开发教程](../../../module_usage/tutorials/ocr_modules/formula_recognition.md)中的中的[二次开发](../../../module_usage/tutorials/ocr_modules/formula_recognition.md#四二次开发)章节,对公式识别模型进行微调。
 
@@ -701,4 +701,4 @@ paddlex --pipeline formula_recognition --input general_formula_recognition.png -
 ```bash
 paddlex --pipeline formula_recognition --input general_formula_recognition.png --device npu:0
 ```
-若您想在更多种类的硬件上使用通用通用公式识别产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。
+若您想在更多种类的硬件上使用公式识别产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition_en.md

@@ -1,14 +1,14 @@
 [简体中文](formula_recognition.md) | English
 
-# General Formula Recognition Pipeline Tutorial
+# Formula Recognition Pipeline Tutorial
 
-## 1. Introduction to the General Formula Recognition Pipeline
+## 1. Introduction to the Formula Recognition Pipeline
 
 Formula recognition is a technology that automatically identifies and extracts LaTeX formula content and its structure from documents or images. It is widely used in document editing and data analysis in fields such as mathematics, physics, and computer science. Leveraging computer vision and machine learning algorithms, formula recognition converts complex mathematical formula information into editable LaTeX format, facilitating further data processing and analysis for users.
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/formula_recognition/01.jpg)
 
-**The General Formula Recognition Pipeline comprises a layout detection module and a formula recognition module.**
+**The Formula Recognition Pipeline comprises a layout detection module and a formula recognition module.**
 
 **If you prioritize model accuracy, choose a model with higher accuracy. If you prioritize inference speed, select a model with faster inference. If you prioritize model size, choose a model with a smaller storage footprint.**
 
@@ -109,7 +109,7 @@ The visualized image not saved by default. You can customize the save path throu
 
 
 #### 2.2 Python Script Integration
-* Quickly perform inference on the pipeline with just a few lines of code, taking the general formula recognition pipeline as an example:
+* Quickly perform inference on the pipeline with just a few lines of code, taking the formula recognition pipeline as an example:
 
 ```python
 from paddlex import create_pipeline
@@ -125,7 +125,7 @@ for res in output:
 
 The Python script above executes the following steps:
 
-（1）Instantiate the general formula recognition pipeline object using `create_pipeline`: Specific parameter descriptions are as follows:
+（1）Instantiate the formula recognition pipeline object using `create_pipeline`: Specific parameter descriptions are as follows:
 
 | Parameter | Description | Type | Default |
 |-|-|-|-|
@@ -133,7 +133,7 @@ The Python script above executes the following steps:
 |`device`| The device for pipeline model inference. Supports: "gpu", "cpu". |`str`|`gpu`|
 |`use_hpip`| Whether to enable high-performance inference, only available if the pipeline supports it. |`bool`|`False`|
 
-（2）Invoke the `predict` method of the general formula recognition pipeline object for inference prediction: The `predict` method parameter is `x`, which is used to input data to be predicted, supporting multiple input methods, as shown in the following examples:
+（2）Invoke the `predict` method of the formula recognition pipeline object for inference prediction: The `predict` method parameter is `x`, which is used to input data to be predicted, supporting multiple input methods, as shown in the following examples:
 
 | Parameter Type | Parameter Description |
 |---------------|-----------------------------------------------------------------------------------------------------------|
@@ -154,7 +154,7 @@ The Python script above executes the following steps:
 | save_to_json | Saves results as a json file   | `- save_path`: str, the path to save the file, when it's a directory, the saved file name is consistent with the input file type;<br>`- indent`: int, json formatting setting, default is 4;<br>`- ensure_ascii`: bool, json formatting setting, default is False; |
 | save_to_img  | Saves results as an image file | `- save_path`: str, the path to save the file, when it's a directory, the saved file name is consistent with the input file type; |
 
-If you have a configuration file, you can customize the configurations of the general formula recognition pipeline by simply modifying the `pipeline` parameter in the `create_pipeline` method to the path of the pipeline configuration file.
+If you have a configuration file, you can customize the configurations of the formula recognition pipeline by simply modifying the `pipeline` parameter in the `create_pipeline` method to the path of the pipeline configuration file.
 
 For example, if your configuration file is saved at `./my_path/formula_recognition.yaml`, you only need to execute:
 
@@ -168,9 +168,9 @@ for res in output:
 ```
 
 ## 3. Development Integration/Deployment
-If the general formula recognition pipeline meets your requirements for inference speed and accuracy, you can proceed directly with development integration/deployment.
+If the formula recognition pipeline meets your requirements for inference speed and accuracy, you can proceed directly with development integration/deployment.
 
-If you need to apply the general formula recognition pipeline directly in your Python project, refer to the example code in [2.2 Python Script Integration](#22-python-script-integration).
+If you need to apply the formula recognition pipeline directly in your Python project, refer to the example code in [2.2 Python Script Integration](#22-python-script-integration).
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
@@ -644,10 +644,10 @@ You can choose the appropriate deployment method based on your needs to proceed
 
 
 ## 4. Custom Development
-If the default model weights provided by the general formula recognition pipeline do not meet your requirements for accuracy or speed in your specific scenario, you can try to further fine-tune the existing models using **your own domain-specific or application-specific data** to improve the recognition performance of the general formula recognition pipeline in your scenario.
+If the default model weights provided by the formula recognition pipeline do not meet your requirements for accuracy or speed in your specific scenario, you can try to further fine-tune the existing models using **your own domain-specific or application-specific data** to improve the recognition performance of the formula recognition pipeline in your scenario.
 
 ### 4.1 Model Fine-tuning
-Since the general formula recognition pipeline consists of two modules (layout detection and formula recognition), unsatisfactory performance may stem from either module.
+Since the formula recognition pipeline consists of two modules (layout detection and formula recognition), unsatisfactory performance may stem from either module.
 
 You can analyze images with poor recognition results. If you find that many formula are undetected (i.e., formula miss detection), it may indicate that the layout detection model needs improvement. You should refer to the [Customization](../../../module_usage/tutorials/ocr_modules/layout_detection_en.md#iv-custom-development) section in the [Layout Detection Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/layout_detection_en.md) and use your private dataset to fine-tune the layout detection model. If many recognition errors occur in detected formula (i.e., the recognized formula content does not match the actual formula content), it suggests that the formula recognition model requires further refinement. You should refer to the [Customization](../../../module_usage/tutorials/ocr_modules/formula_recognition_en.md#iv-custom-development) section in the [Formula Recognition Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/formula_recognition_en.md) and fine-tune the formula recognition model.
 
@@ -683,4 +683,4 @@ Now, if you want to switch the hardware to Ascend NPU, you only need to modify t
 paddlex --pipeline formula_recognition --input general_formula_recognition.png --device npu:0
 ```
 
-If you want to use the general formula recognition pipeline on more types of hardware, please refer to the [PaddleX Multi-Hardware Usage Guide](../../../other_devices_support/multi_devices_use_guide_en.md).
+If you want to use the formula recognition pipeline on more types of hardware, please refer to the [PaddleX Multi-Hardware Usage Guide](../../../other_devices_support/multi_devices_use_guide_en.md).