Hugging Face's logo

tadkt
/
GOT_Vietnamese

Image-Text-to-Text
Transformers
Safetensors
Vietnamese
English
GOT
feature-extraction
got
vision-language
ocr2.0
got_vietnamese
custom_code
Model card Files
xet
 Community
1
tadkt commited on
Commit
53de88a
·
verified ·
1 Parent(s): 6adb3be

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -12
README.md CHANGED
@@ -30,17 +30,5 @@ model = model.eval().cuda()
30
  image_file = 'xxx.jpg'
31
  # plain texts OCR
32
  res = model.chat(tokenizer, image_file, ocr_type='ocr')
33
- # format texts OCR:
34
- # res = model.chat(tokenizer, image_file, ocr_type='format')
35
- # fine-grained OCR:
36
- # res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_box='')
37
- # res = model.chat(tokenizer, image_file, ocr_type='format', ocr_box='')
38
- # res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_color='')
39
- # res = model.chat(tokenizer, image_file, ocr_type='format', ocr_color='')
40
- # multi-crop OCR:
41
- # res = model.chat_crop(tokenizer, image_file, ocr_type='ocr')
42
- # res = model.chat_crop(tokenizer, image_file, ocr_type='format')
43
- # render the formatted OCR results:
44
- # res = model.chat(tokenizer, image_file, ocr_type='format', render=True, save_render_file = './demo.html')
45
  print(res)
46
  ```
 
30
  image_file = 'xxx.jpg'
31
  # plain texts OCR
32
  res = model.chat(tokenizer, image_file, ocr_type='ocr')
 
 
 
 
 
 
 
 
 
 
 
 
33
  print(res)
34
  ```