Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
vision
ocr
trocr
handwriting-recognition
document-processing
Instructions to use WARAJA/Tzefa-Word-OCR-TrOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WARAJA/Tzefa-Word-OCR-TrOCR 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="WARAJA/Tzefa-Word-OCR-TrOCR")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("WARAJA/Tzefa-Word-OCR-TrOCR") model = AutoModelForMultimodalLM.from_pretrained("WARAJA/Tzefa-Word-OCR-TrOCR") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- a04d863bb5f2e897eaeff42b42b4986a2321707613b7799fd1a573d3ce58994d
- Size of remote file:
- 1.06 kB
- SHA256:
- bebe1b039d0b9ca59030ce4a7145e01d3bfc39525882a328bcdbf8faabd4ae56
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.