Instructions to use microsoft/trocr-base-str with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-base-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-base-str")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-str") model = AutoModelForMultimodalLM.from_pretrained("microsoft/trocr-base-str", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from microsoft/trocr-base-str: direct link, hf CLI and curl.
- Browser
- Download file 1.34 GB
-
https://huggingface.co/microsoft/trocr-base-str/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://microsoft/trocr-base-str/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/microsoft/trocr-base-str/resolve/main/pytorch_model.bin
1.34 GB
- Xet hash:
- ed70109029f56788b3cbfccfa15cac2da84d71e7d98905ab68741a2c40521268
- Size of remote file:
- 1.34 GB
- SHA256:
- eaff179cd469b751f3afa999ca3ed0ab178373e8b46ad060342cabd8cc277085
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.