How to use katanaml/donut-demo 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="katanaml/donut-demo")
# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("katanaml/donut-demo") model = AutoModelForImageTextToText.from_pretrained("katanaml/donut-demo")
Donut model finetuned with CORD dataset. Mean accuracy: 0.901198895445646
