Instructions to use microsoft/trocr-large-str with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-large-str 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-str")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-large-str") model = AutoModelForMultimodalLM.from_pretrained("microsoft/trocr-large-str", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from microsoft/trocr-large-str: direct link, hf CLI and curl.
- Browser
- Download file 2.23 GB
-
https://huggingface.co/microsoft/trocr-large-str/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://microsoft/trocr-large-str/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/microsoft/trocr-large-str/resolve/main/pytorch_model.bin
2.23 GB
- Xet hash:
- c120e959b930261474a700613b308e771c50645a7410ae1cf7a01c7096bc9fa0
- Size of remote file:
- 2.23 GB
- SHA256:
- 1ed7e3cff471bcc919812450bc3cee3e7143d2849cdf97fe44fe3995769ba949
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.