How to use gg4ever/trOCR-final 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="gg4ever/trOCR-final")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("gg4ever/trOCR-final") model = AutoModelForMultimodalLM.from_pretrained("gg4ever/trOCR-final", device_map="auto")
https://huggingface.co/gg4ever/trOCR-final/resolve/refs%2Fpr%2F1/tokenizer.json
hf download hf://gg4ever/trOCR-final@refs/pr/1/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/gg4ever/trOCR-final/resolve/refs%2Fpr%2F1/tokenizer.json
