Image-to-Text
Transformers
Safetensors
Latin
French
esp
vision-encoder-decoder
image-text-to-text
trocr
Eval Results (legacy)
Instructions to use medieval-data/trocr-medieval-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use medieval-data/trocr-medieval-base 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="medieval-data/trocr-medieval-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("medieval-data/trocr-medieval-base") model = AutoModelForMultimodalLM.from_pretrained("medieval-data/trocr-medieval-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download logo-base.png from medieval-data/trocr-medieval-base: direct link, hf CLI and curl.
- Browser
- Download file 131 kB
-
https://huggingface.co/medieval-data/trocr-medieval-base/resolve/main/logo-base.png
- Command line
-
hf download hf://medieval-data/trocr-medieval-base/logo-base.png
-
curl -L -o logo-base.png https://huggingface.co/medieval-data/trocr-medieval-base/resolve/main/logo-base.png
131 kB
