Image-to-Text
Transformers
PyTorch
Korean
vision-encoder-decoder
image-text-to-text
donut
document-understanding
ocr-free
korean
Instructions to use ksk00/donut-docai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ksk00/donut-docai with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="ksk00/donut-docai")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("ksk00/donut-docai") model = AutoModelForMultimodalLM.from_pretrained("ksk00/donut-docai") - Notebooks
- Google Colab
- Kaggle
| { | |
| "do_align_long_axis": true, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_thumbnail": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "DonutImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "DonutProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 2560, | |
| "width": 1920 | |
| } | |
| } | |