Instructions to use microsoft/trocr-base-printed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-base-printed 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="microsoft/trocr-base-printed")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-printed") model = AutoModelForMultimodalLM.from_pretrained("microsoft/trocr-base-printed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update preprocessor_config.json
Verified signature5cd6a54 -
Update preprocessor_config.json (#10)
Verified signature- Update preprocessor_config.json (d8a07658d30f42946ad9f1d1222d47bdbb5dfb51) Co-authored-by: Rohit <rohit5895@users.noreply.huggingface.co>618e2fd
-
First commit
5fecfdb