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 signatureUpdate image processord8a0765
-
Adding generation config file(s)
0c708d3
-
Update README.md
59889fe
-
Update README.md (#1)
- Update README.md (dde50d9ce4c629fd0004bfc4e1c9b5ef092a4fb3) Co-authored-by: Loïck BOURDOIS <lbourdois@users.noreply.huggingface.co>191a64d
-
Remove tokenizer_file
822aa45
-
Update code example
bc285bd
-
Add more appropriate image to code example
ba8ea5c -
Add trocr tag
eb7bf98
-
Rename encoder_hidden_size to cross_attention_hidden_size
11abf67 -
Add model card
7bbc2cb
-
First commit
5fecfdb -
initial commit
a8a4689