Instructions to use microsoft/trocr-large-printed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-large-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-large-printed")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-large-printed") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-large-printed") - Notebooks
- Google Colab
- Kaggle
π Documentation Enhancement Suggestion
#8 opened 3 months ago
by
CroviaTrust
π Documentation Enhancement Suggestion
#7 opened 3 months ago
by
CroviaTrust
Adding ONNX file of this model
#6 opened 6 months ago
by
ev4shin
How to get text position in TR-OCR
πβ€οΈ 2
4
#5 opened almost 2 years ago
by
maifeeulasad