Hugging Face's logo

PaddlePaddle
/
PaddleOCR-VL-1.6

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
15
ChengCui commited on
Commit
548d951
·
verified ·
1 Parent(s): 2072f56

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -13
README.md CHANGED
@@ -277,59 +277,55 @@ model = AutoModelForImageTextToText.from_pretrained(model_path, torch_dtype=torc
277
  ## Visualization
278
 
279
 
280
- ### Real-word Document Parsing
281
-
282
-
283
- #### Illumination
284
 
285
  <div align="center">
286
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/light.jpg" width="800"/>
287
  </div>
288
 
289
 
290
- #### Skew
291
 
292
  <div align="center">
293
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/skew.jpg" width="800"/>
294
  </div>
295
 
296
 
297
- #### Screen Photography
298
 
299
  <div align="center">
300
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/screen.jpg" width="800"/>
301
  </div>
302
 
303
 
304
- #### Scanning
305
 
306
  <div align="center">
307
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/scaning.jpg" width="800"/>
308
  </div>
309
 
310
- #### Warping
311
 
312
  <div align="center">
313
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/curving.jpg" width="800"/>
314
  </div>
315
 
316
 
317
- ### Text Spotting
318
 
319
 
320
  <div align="center">
321
- <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/spotting.jpg" width="800"/>
322
  </div>
323
 
324
 
325
- ### Seal Recognition
326
 
327
 
328
  <div align="center">
329
- <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/seal.jpg" width="800"/>
330
  </div>
331
 
332
-
333
  ## Acknowledgments
334
 
335
  We would like to thank [PaddleFormers](https://github.com/PaddlePaddle/PaddleFormers), [Keye](https://github.com/Kwai-Keye/Keye), [MinerU](https://github.com/opendatalab/MinerU), [OmniDocBench](https://github.com/opendatalab/OmniDocBench) for providing valuable code, model weights and benchmarks. We also appreciate everyone's contribution to this open-source project!
 
277
  ## Visualization
278
 
279
 
280
+ #### Table Recognition
 
 
 
281
 
282
  <div align="center">
283
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/light.jpg" width="800"/>
284
  </div>
285
 
286
 
287
+ #### Chart Parsing
288
 
289
  <div align="center">
290
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/skew.jpg" width="800"/>
291
  </div>
292
 
293
 
294
+ #### Formula Recognition
295
 
296
  <div align="center">
297
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/screen.jpg" width="800"/>
298
  </div>
299
 
300
 
301
+ #### Chinese Ancient Document Recognition
302
 
303
  <div align="center">
304
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/scaning.jpg" width="800"/>
305
  </div>
306
 
307
+ #### Chinese Rare Character Recognition
308
 
309
  <div align="center">
310
  <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/curving.jpg" width="800"/>
311
  </div>
312
 
313
 
314
+ ### Seal Recognition
315
 
316
 
317
  <div align="center">
318
+ <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/seal.jpg" width="800"/>
319
  </div>
320
 
321
 
322
+ ### Real-world Low-Quality Document Parsing
323
 
324
 
325
  <div align="center">
326
+ <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/spotting.jpg" width="800"/>
327
  </div>
328
 
 
329
  ## Acknowledgments
330
 
331
  We would like to thank [PaddleFormers](https://github.com/PaddlePaddle/PaddleFormers), [Keye](https://github.com/Kwai-Keye/Keye), [MinerU](https://github.com/opendatalab/MinerU), [OmniDocBench](https://github.com/opendatalab/OmniDocBench) for providing valuable code, model weights and benchmarks. We also appreciate everyone's contribution to this open-source project!