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", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 134 Bytes
c0ba2a1 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:1c42979ff5e88e2a28f952162e8a2a9762c9bfe997bb71ab9384ff97d893ec23
size 809179350
|