Ocr v5 (#4056)

* refine PP-OCRv5_det docs

* refine docs and configs

docs/module_usage/tutorials/ocr_modules/text_detection.en.md

@@ -23,16 +23,16 @@ The text detection module is a crucial component in OCR (Optical Character Recog
 <tr>
 <td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
 <td>83.8</td>
-<td>- / -</td>
-<td>- / -</td>
-<td>101</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
 <td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
 <td>79.0</td>
-<td>- / -</td>
-<td>- / -</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
 <td>4.7</td>
 <td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>

docs/module_usage/tutorials/ocr_modules/text_detection.md

@@ -25,16 +25,16 @@ comments: true
 <tr>
 <td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
 <td>83.8</td>
-<td>- / -</td>
-<td>- / -</td>
-<td>101</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
 <td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
 </tr>
 <tr>
 <td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
 <td>79.0</td>
-<td>- / -</td>
-<td>- / -</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
 <td>4.7</td>
 <td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
 </tr>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.en.md

@@ -136,20 +136,36 @@ The <b>PP-ChatOCRv3-doc</b> pipeline includes modules for <b>Table Structure Rec
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">Training Model</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
-<td>PP-OCRv4's server-side text detection model, featuring higher accuracy, suitable for deployment on high-performance servers</td>
+<td>PP-OCRv4 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
-<td>PP-OCRv4's mobile text detection model, optimized for efficiency, suitable for deployment on edge devices</td>
+<td>PP-OCRv4 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>
 </tbody>
 </table>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.md

@@ -136,8 +136,24 @@ comments: true
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
@@ -145,7 +161,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
@@ -1821,7 +1837,7 @@ print(result_chat["chatResult"])
 SubModules:
     TextDetection:
     module_name: text_detection
-    model_name: PP-OCRv4_server_det
+    model_name: PP-OCRv5_server_det
     model_dir: null # 替换为微调后的文本检测模型权重路径
     limit_side_len: 960
     limit_type: max
@@ -1832,7 +1848,7 @@ SubModules:
 
     TextRecognition:
     module_name: text_recognition
-    model_name: PP-OCRv4_server_rec
+    model_name: PP-OCRv5_server_rec
     model_dir: null # 替换为微调后的文本识别模型权重路径
     batch_size: 1
             score_thresh: 0

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.en.md

@@ -227,20 +227,36 @@ The Document Scene Information Extraction v4 pipeline includes modules for **Lay
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">Training Model</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
-<td>PP-OCRv4's server-side text detection model, featuring higher accuracy, suitable for deployment on high-performance servers</td>
+<td>PP-OCRv4 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
-<td>PP-OCRv4's mobile text detection model, optimized for efficiency, suitable for deployment on edge devices</td>
+<td>PP-OCRv4 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>
 </tbody>
 </table>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.md

@@ -204,8 +204,24 @@ comments: true
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td>
-<td>82.56</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
@@ -213,7 +229,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>77.35</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
@@ -221,7 +237,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>78.68</td>
+<td>精度接近 PP-OCRv4_mobile_det</td>
 <td>8.44 / 2.91</td>
 <td>27.87 / 27.87</td>
 <td>2.1</td>
@@ -229,7 +245,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">训练模型</a></td>
-<td>80.11</td>
+<td>精度接近 PP-OCRv4_server_det</td>
 <td>65.41 / 13.67</td>
 <td>305.07 / 305.07</td>
 <td>102.1</td>

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.en.md

@@ -74,16 +74,16 @@ The General OCR pipeline is designed to solve text recognition tasks, extracting
 <tr>
 <td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
 <td>83.8</td>
-<td>- / -</td>
-<td>- / -</td>
-<td>101</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
 <td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
 <td>79.0</td>
-<td>- / -</td>
-<td>- / -</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
 <td>4.7</td>
 <td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md

@@ -72,18 +72,19 @@ OCR（光学字符识别，Optical Character Recognition）是一种将图像中
 </tr>
 </thead>
 <tbody>
+<tr>
 <td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
 <td>83.8</td>
-<td>- / -</td>
-<td>- / -</td>
-<td>101</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
 <td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
 </tr>
 <tr>
 <td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
 <td>79.0</td>
-<td>- / -</td>
-<td>- / -</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
 <td>4.7</td>
 <td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
 </tr>
@@ -104,20 +105,20 @@ OCR（光学字符识别，Optical Character Recognition）是一种将图像中
 <td>PP-OCRv4 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
 </tr>
 <tr>
-<td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>Accuracy comparable to PP-OCRv4_mobile_det</td>
+<td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>精度接近 PP-OCRv4_mobile_det</td>
 <td>8.44 / 2.91</td>
 <td>27.87 / 27.87</td>
 <td>2.1</td>
-<td>PP-OCRv3 mobile text detection model with higher efficiency, suitable for edge device deployment</td>
+<td>PP-OCRv3 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
 </tr>
 <tr>
-<td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">Training Model</a></td>
-<td>Accuracy comparable to PP-OCRv4_server_det</td>
+<td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">训练模型</a></td>
+<td>精度接近 PP-OCRv4_server_det</td>
 <td>65.41 / 13.67</td>
 <td>305.07 / 305.07</td>
 <td>102.1</td>
-<td>PP-OCRv3 server text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+<td>PP-OCRv3 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
 </tr>
 </tbody>
 </table>

docs/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.en.md

@@ -201,36 +201,52 @@ Layout parsing is a technology that extracts structured information from documen
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">Training Model</a></td>
-<td>82.56</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
-<td>The server-side text detection model of PP-OCRv4, with higher accuracy, suitable for deployment on high-performance servers.</td>
+<td>PP-OCRv4 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>77.35</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
-<td>The mobile text detection model of PP-OCRv4, with higher efficiency, suitable for deployment on edge devices.</td>
+<td>PP-OCRv4 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>
 <tr>
 <td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>78.68</td>
+<td>Accuracy comparable to PP-OCRv4_mobile_det</td>
 <td>8.44 / 2.91</td>
 <td>27.87 / 27.87</td>
 <td>2.1</td>
-<td>The mobile text detection model of PP-OCRv3, with higher efficiency, suitable for deployment on edge devices.</td>
+<td>PP-OCRv3 mobile text detection model with higher efficiency, suitable for edge device deployment</td>
 </tr>
 <tr>
 <td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">Training Model</a></td>
-<td>80.11</td>
+<td>Accuracy comparable to PP-OCRv4_server_det</td>
 <td>65.41 / 13.67</td>
 <td>305.07 / 305.07</td>
 <td>102.1</td>
-<td>The server-side text detection model of PP-OCRv3, with higher accuracy, suitable for deployment on high-performance servers.</td>
+<td>PP-OCRv3 server text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 </tbody>
 </table>

docs/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.md

@@ -183,8 +183,24 @@ comments: true
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td>
-<td>82.56</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
@@ -192,7 +208,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>77.35</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
@@ -200,7 +216,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>78.68</td>
+<td>精度接近 PP-OCRv4_mobile_det</td>
 <td>8.44 / 2.91</td>
 <td>27.87 / 27.87</td>
 <td>2.1</td>
@@ -208,7 +224,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">训练模型</a></td>
-<td>80.11</td>
+<td>精度接近 PP-OCRv4_server_det</td>
 <td>65.41 / 13.67</td>
 <td>305.07 / 305.07</td>
 <td>102.1</td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.en.md

@@ -224,20 +224,52 @@ The <b>General Layout Parsing Pipeline</b> includes modules for table structure
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">Training Model</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
-<td>PP-OCRv4's server-side text detection model, featuring higher accuracy, suitable for deployment on high-performance servers</td>
+<td>PP-OCRv4 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
-<td>PP-OCRv4's mobile text detection model, optimized for efficiency, suitable for deployment on edge devices</td>
+<td>PP-OCRv4 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
+<td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>Accuracy comparable to PP-OCRv4_mobile_det</td>
+<td>8.44 / 2.91</td>
+<td>27.87 / 27.87</td>
+<td>2.1</td>
+<td>PP-OCRv3 mobile text detection model with higher efficiency, suitable for edge device deployment</td>
+</tr>
+<tr>
+<td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">Training Model</a></td>
+<td>Accuracy comparable to PP-OCRv4_server_det</td>
+<td>65.41 / 13.67</td>
+<td>305.07 / 305.07</td>
+<td>102.1</td>
+<td>PP-OCRv3 server text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 </tbody>
 </table>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md

@@ -202,8 +202,24 @@ comments: true
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td>
-<td>82.56</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
@@ -211,7 +227,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>77.35</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
@@ -219,7 +235,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv3_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>78.68</td>
+<td>精度接近 PP-OCRv4_mobile_det</td>
 <td>8.44 / 2.91</td>
 <td>27.87 / 27.87</td>
 <td>2.1</td>
@@ -227,7 +243,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv3_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_server_det_pretrained.pdparams">训练模型</a></td>
-<td>80.11</td>
+<td>精度接近 PP-OCRv4_server_det</td>
 <td>65.41 / 13.67</td>
 <td>305.07 / 305.07</td>
 <td>102.1</td>
@@ -1623,7 +1639,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_det
+        model_name: PP-OCRv5_server_det
         model_dir: null # 替换为微调后的文本测模型权重路径
         limit_side_len: 960
         limit_type: max
@@ -1634,7 +1650,7 @@ SubPipelines:
 
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec
+        model_name: PP-OCRv5_server_rec
         model_dir: null # 替换为微调后的文本识别模型权重路径
         batch_size: 1
         score_thresh: 0

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md

@@ -1422,7 +1422,7 @@ SubPipelines:
         ...
         TextRecognition:
           module_name: text_recognition
-          model_name: PP-OCRv4_server_rec
+          model_name: PP-OCRv5_server_rec
           model_dir: null # Modify this to the local path of the fine-tuned text recognition model weights
         ...
 ```

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md

@@ -1440,7 +1440,7 @@ SubPipelines:
         ...
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec
+        model_name: PP-OCRv5_server_rec
         model_dir: null # 修改此处为微调后的文本识别模型权重的本地路径
         ...
 ```

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.en.md

@@ -57,20 +57,36 @@ The General Table Recognition Pipeline is designed to solve table recognition ta
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">Training Model</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
-<td>The server text detection model of PP-OCRv4, with higher accuracy, suitable for deployment on high-performance servers.</td>
+<td>PP-OCRv4 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
-<td>The mobile text detection model of PP-OCRv4, which is more efficient and suitable for deployment on edge devices.</td>
+<td>PP-OCRv4 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>
 </tbody>
 </table>
@@ -1460,7 +1476,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_det
+        model_name: PP-OCRv5_server_det
         model_dir: null # Replace with fine-tuned model weight paths
         limit_side_len: 960
         limit_type: max
@@ -1470,7 +1486,7 @@ SubPipelines:
         unclip_ratio: 1.5
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec
+        model_name: PP-OCRv5_server_rec
         model_dir: null # Replace with fine-tuned model weight paths
         batch_size: 1
         score_thresh: 0

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -57,8 +57,24 @@ comments: true
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
@@ -66,7 +82,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
@@ -1403,7 +1419,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_det
+        model_name: PP-OCRv5_server_det
         model_dir: null # 替换为微调后的文本检测模型权重路径
         limit_side_len: 960
         limit_type: max
@@ -1413,7 +1429,7 @@ SubPipelines:
         unclip_ratio: 1.5
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec
+        model_name: PP-OCRv5_server_rec
         model_dir: null # 替换为微调后文本识别的模型权重路径
         batch_size: 1
         score_thresh: 0

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.en.md

@@ -99,20 +99,36 @@ The General Table Recognition v2 Pipeline (PP-TableMagic) is designed to solve t
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">Training Model</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">Training Model</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">Training Model</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
-<td>The server-side text detection model of PP-OCRv4, with higher precision, suitable for deployment on high-performance servers.</td>
+<td>PP-OCRv4 server-side text detection model with higher accuracy, suitable for deployment on high-performance servers</td>
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">Training Model</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
-<td>The mobile text detection model of PP-OCRv4, with higher efficiency, suitable for deployment on edge devices.</td>
+<td>PP-OCRv4 mobile-side text detection model with higher efficiency, suitable for deployment on edge devices</td>
 </tr>
 </tbody>
 </table>
@@ -1671,7 +1687,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_det
+        model_name: PP-OCRv5_server_det
         model_dir: null
         limit_side_len: 960
         limit_type: max
@@ -1682,7 +1698,7 @@ SubPipelines:
 
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec
+        model_name: PP-OCRv5_server_rec
         model_dir: null
         batch_size: 1
         score_thresh: 0

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.md

@@ -100,8 +100,24 @@ comments: true
 </thead>
 <tbody>
 <tr>
+<td>PP-OCRv5_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_det_pretrained.pdparams">训练模型</a></td>
+<td>83.8</td>
+<td>89.55 / 70.19</td>
+<td>371.65 / 371.65</td>
+<td>84.3</td>
+<td>PP-OCRv5 的服务端文本检测模型，精度更高，适合在性能较好的服务器上部署</td>
+</tr>
+<tr>
+<td>PP-OCRv5_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_det_pretrained.pdparams">训练模型</a></td>
+<td>79.0</td>
+<td>8.79 / 3.13</td>
+<td>51.00 / 28.58</td>
+<td>4.7</td>
+<td>PP-OCRv5 的移动端文本检测模型，效率更高，适合在端侧设备部署</td>
+</tr>
+<tr>
 <td>PP-OCRv4_server_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td>
-<td>82.69</td>
+<td>69.2</td>
 <td>83.34 / 80.91</td>
 <td>442.58 / 442.58</td>
 <td>109</td>
@@ -109,7 +125,7 @@ comments: true
 </tr>
 <tr>
 <td>PP-OCRv4_mobile_det</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams">训练模型</a></td>
-<td>77.79</td>
+<td>63.8</td>
 <td>8.79 / 3.13</td>
 <td>51.00 / 28.58</td>
 <td>4.7</td>
@@ -1675,7 +1691,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_det
+        model_name: PP-OCRv5_server_det
         model_dir: null # 替换为微调后的文本检测模型权重路径
         limit_side_len: 960
         limit_type: max
@@ -1686,7 +1702,7 @@ SubPipelines:
 
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec_doc
+        model_name: PP-OCRv5_server_rec
         model_dir: null # 替换为微调后文本识别的模型权重路径
         batch_size: 1
         score_thresh: 0