Hugging Face's logo

PaddlePaddle
/
PaddleOCR-VL-1.5

Image-Text-to-Text
PaddleOCR
Safetensors
English
Chinese
multilingual
paddleocr_vl
ERNIE4.5
PaddlePaddle
image-to-text
ocr
document-parse
layout
table
formula
chart
seal
spotting
conversational
custom_code
Eval Results
Model card Files
xet
 Community
28
gggdddfff commited on
Commit
83ebf23
·
verified ·
1 Parent(s): 89769a8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -7
README.md CHANGED
@@ -88,25 +88,22 @@ Install [PaddlePaddle](https://www.paddlepaddle.org.cn/install/quick) and [Paddl
88
  ```bash
89
  # The following command installs the PaddlePaddle version for CUDA 12.6. For other CUDA versions and the CPU version, please refer to https://www.paddlepaddle.org.cn/en/install/quick?docurl=/documentation/docs/en/develop/install/pip/linux-pip_en.html
90
  python -m pip install paddlepaddle-gpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
91
- python -m pip install -U "paddleocr[doc-parser]"
92
  ```
93
 
94
- > **Please ensure that you install PaddlePaddle framework version 3.2.1 or above, along with the special version of safetensors.** For macOS users, please use Docker to set up the environment.
95
-
96
-
97
  ### Basic Usage
98
 
99
  CLI usage:
100
 
101
  ```bash
102
- paddleocr doc_parser -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png
103
  ```
104
 
105
  Python API usage:
106
 
107
  ```python
108
  from paddleocr import PaddleOCRVL
109
- pipeline = PaddleOCRVL()
110
  output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png")
111
  for res in output:
112
  res.print()
@@ -137,12 +134,13 @@ for res in output:
137
  ```bash
138
  paddleocr doc_parser \
139
  -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png \
 
140
  --vl_rec_backend vllm-server \
141
  --vl_rec_server_url http://127.0.0.1:8080/v1
142
  ```
143
  ```python
144
  from paddleocr import PaddleOCRVL
145
- pipeline = PaddleOCRVL(vl_rec_backend="vllm-server", vl_rec_server_url="http://127.0.0.1:8080/v1")
146
  output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png")
147
  for res in output:
148
  res.print()
 
88
  ```bash
89
  # The following command installs the PaddlePaddle version for CUDA 12.6. For other CUDA versions and the CPU version, please refer to https://www.paddlepaddle.org.cn/en/install/quick?docurl=/documentation/docs/en/develop/install/pip/linux-pip_en.html
90
  python -m pip install paddlepaddle-gpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
91
+ python -m pip install -U "paddleocr[doc-parser]>=3.4.0"
92
  ```
93
 
 
 
 
94
  ### Basic Usage
95
 
96
  CLI usage:
97
 
98
  ```bash
99
+ paddleocr doc_parser -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png --pipeline_version v1.5
100
  ```
101
 
102
  Python API usage:
103
 
104
  ```python
105
  from paddleocr import PaddleOCRVL
106
+ pipeline = PaddleOCRVL(pipeline_version="v1.5")
107
  output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png")
108
  for res in output:
109
  res.print()
 
134
  ```bash
135
  paddleocr doc_parser \
136
  -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png \
137
+ --pipeline_version v1.5 \
138
  --vl_rec_backend vllm-server \
139
  --vl_rec_server_url http://127.0.0.1:8080/v1
140
  ```
141
  ```python
142
  from paddleocr import PaddleOCRVL
143
+ pipeline = PaddleOCRVL(pipeline_version="v1.5", vl_rec_backend="vllm-server", vl_rec_server_url="http://127.0.0.1:8080/v1")
144
  output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/paddleocr_vl_demo.png")
145
  for res in output:
146
  res.print()