Instructions to use microsoft/trocr-large-handwritten with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-large-handwritten 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-handwritten")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-large-handwritten") model = AutoModelForMultimodalLM.from_pretrained("microsoft/trocr-large-handwritten") - Notebooks
- Google Colab
- Kaggle
Is there a way to get the recognition scores?
#4
by mfg12 - opened
Hi!!!,
I've been looking through the documentation, but couldn't find anything about scores. I don't know if it's possible or simply this model doesn't take them out.
Thank's
install jiwer library , use CER and WER