update note about Model Source (#4459)

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

@@ -101,7 +101,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running, the result obtained is:
 

docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md

@@ -100,7 +100,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 ```bash

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

@@ -158,7 +158,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running, the result obtained is:
 

docs/module_usage/tutorials/ocr_modules/formula_recognition.md

@@ -157,7 +157,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 ```bash

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

@@ -324,7 +324,7 @@ for res in output:
 
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 <details><summary>👉 <b>After running, the result is: (Click to expand)</b></summary>
 

docs/module_usage/tutorials/ocr_modules/layout_detection.md

@@ -326,7 +326,7 @@ for res in output:
 
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 <details><summary>👉 <b>运行后，得到的结果为：（点击展开）</b></summary>
 

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

@@ -110,7 +110,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running, the result is:
 

docs/module_usage/tutorials/ocr_modules/seal_text_detection.md

@@ -107,7 +107,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 

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

@@ -100,7 +100,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 <details><summary>👉 <b>After running, the result is: (Click to expand)</b></summary>
 

docs/module_usage/tutorials/ocr_modules/table_cells_detection.md

@@ -99,7 +99,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 <details><summary>👉 <b>运行后，得到的结果为：（点击展开）</b></summary>
 

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

@@ -92,7 +92,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running the code, the result obtained is:
 

docs/module_usage/tutorials/ocr_modules/table_classification.md

@@ -91,7 +91,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 ```

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

@@ -119,7 +119,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 <details><summary>👉 <b>After running, the result is: (Click to expand)</b></summary>
 

docs/module_usage/tutorials/ocr_modules/table_structure_recognition.md

@@ -115,7 +115,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 <details><summary>👉 <b>运行后，得到的结果为：（点击展开）</b></summary>
 

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

@@ -144,7 +144,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running, the result obtained is:
 

docs/module_usage/tutorials/ocr_modules/text_detection.md

@@ -143,7 +143,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 

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

@@ -103,7 +103,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running, the result obtained is:
 

docs/module_usage/tutorials/ocr_modules/text_image_unwarping.md

@@ -97,7 +97,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 

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

@@ -476,7 +476,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 For more information on using PaddleX's single-model inference APIs, please refer to the [PaddleX Single-Model Python Script Usage Instructions](../../instructions/model_python_API.en.md).
 

docs/module_usage/tutorials/ocr_modules/text_recognition.md

@@ -501,7 +501,7 @@ for res in output:
     res.save_to_json(save_path="./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 ```bash

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

@@ -112,7 +112,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 After running, the result obtained is:
 

docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.md

@@ -112,7 +112,7 @@ for res in output:
     res.save_to_json("./output/res.json")
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 运行后，得到的结果为：
 ```bash

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

@@ -1851,7 +1851,7 @@ paddlex --pipeline OCR \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 For details on the relevant parameter descriptions, please refer to the parameter descriptions in [2.2.2 Python Script Integration](#222-python-script-integration). Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md

@@ -1843,7 +1843,7 @@ paddlex --pipeline OCR \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.2.2 Python脚本方式集成](#222-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -1340,7 +1340,7 @@ paddlex --pipeline PP-StructureV3 \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 The parameter description can be found in [2.2.2 Python Script Integration](#222-python-script-integration). Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

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

@@ -1305,7 +1305,7 @@ paddlex --pipeline PP-StructureV3 \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.2.2 Python脚本方式集成](#222-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -504,7 +504,7 @@ paddlex --pipeline doc_preprocessor \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 You can refer to the parameter descriptions in [2.1.2 Python Script Integration](#212-python-script-integration) for related parameter details. Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

docs/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.md

@@ -502,7 +502,7 @@ paddlex --pipeline doc_preprocessor \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.1.2 Python脚本方式集成](#212-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -1221,7 +1221,7 @@ paddlex --pipeline formula_recognition \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 The relevant parameter descriptions can be referenced from [2.2 Integration via Python Script](#22-integration-via-python-script). Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -1223,7 +1223,7 @@ paddlex --pipeline formula_recognition \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.2 Python脚本方式集成](#22-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -749,7 +749,7 @@ paddlex --pipeline layout_parsing \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 For parameter descriptions, refer to the parameter explanations in [2.2.2 Integration via Python Script](#222-integration-via-python-script). Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md

@@ -697,7 +697,7 @@ paddlex --pipeline layout_parsing \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.2.2 Python脚本方式集成](#222-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -1364,7 +1364,7 @@ paddlex --pipeline seal_recognition \
     --save_path ./output
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 The relevant parameter descriptions can be referred to in the parameter explanations of [2.1.2 Integration via Python Script](#212-integration-via-python-script). Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md

@@ -1383,7 +1383,7 @@ paddlex --pipeline seal_recognition \
     --save_path ./output
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.1.2 Python脚本方式集成](#212-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -717,7 +717,7 @@ paddlex --pipeline table_recognition \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 The content of the parameters can refer to the parameter description in [2.2 Python Script Method](#22-python-script-method-integration). Supports specifying multiple devices simultaneously for parallel inference. For details, please refer to the documentation on pipeline parallel inference.
 

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -656,7 +656,7 @@ paddlex --pipeline table_recognition \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.2 Python脚本方式](#22-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。
 

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

@@ -1121,7 +1121,7 @@ paddlex --pipeline table_recognition_v2 \
         --device gpu:0
 ```
 
-<b>Note: </b>The official models would be download from HuggingFace by default. If can't access to HuggingFace, please set the environment variable `PADDLE_PDX_MODEL_SOURCE="BOS"` to change the model source to BOS. In the future, more model sources will be supported.
+<b>Note: </b>The official models would be download from HuggingFace by first. PaddleX also support to specify the preferred source by setting the environment variable `PADDLE_PDX_MODEL_SOURCE`. The supported values are `huggingface`, `aistudio`, `bos`, and `modelscope`. For example, to prioritize using `bos`, set: `PADDLE_PDX_MODEL_SOURCE="bos"`.
 
 <details><summary>👉 <b>After running, the result obtained is: (Click to expand)</b></summary>
 

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.md

@@ -1139,7 +1139,7 @@ paddlex --pipeline table_recognition_v2 \
         --device gpu:0
 ```
 
-<b>注：</b>PaddleX 官方模型默认从 HuggingFace 获取，如运行环境访问 HuggingFace 不便，可通过环境变量修改模型源为 BOS：`PADDLE_PDX_MODEL_SOURCE="BOS"`，未来将支持更多主流模型源；
+<b>注：</b>PaddleX 支持多个模型托管平台，官方模型默认优先从 HuggingFace 下载。PaddleX 也支持通过环境变量 `PADDLE_PDX_MODEL_SOURCE` 设置优先使用的托管平台，目前支持 `huggingface`、`aistudio`、`bos`、`modelscope`，如优先使用 `bos`：`PADDLE_PDX_MODEL_SOURCE="bos"`；
 
 相关的参数说明可以参考[2.2 Python脚本方式集成](#22-python脚本方式集成)中的参数说明。支持同时指定多个设备以进行并行推理，详情请参考 [产线并行推理](../../instructions/parallel_inference.md#指定多个推理设备)。