Instructions to use MixTex/ZhEn-Latex-OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MixTex/ZhEn-Latex-OCR 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="MixTex/ZhEn-Latex-OCR")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("MixTex/ZhEn-Latex-OCR") model = AutoModelForMultimodalLM.from_pretrained("MixTex/ZhEn-Latex-OCR") - Notebooks
- Google Colab
- Kaggle
Hello, I am interested in OCR technique, could I use this model in traditional Chinese
#2
by MoleBioL - opened
Hello,
There is a project that I need to use traditional Chinese OCR these days, and I tried Python tesseract in the beginning.
However, it doesn't work as my expectation. Could I use this in traditional Chinese image?
And I am curious... if I wanna finetune a model myself, which technique should I use? Does this model use the LLM techniqe?
Thanks a lot