Instructions to use kha-white/manga-ocr-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kha-white/manga-ocr-base 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="kha-white/manga-ocr-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("kha-white/manga-ocr-base") model = AutoModelForMultimodalLM.from_pretrained("kha-white/manga-ocr-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training the Model
#5
by Aaryan1 - opened
Hi Kha-White
This is an extremely amazing model,
I just wanted to understand how you trained it and how you coded the mode, using what frame works?
Thanks :)
Hi,
The model was trained using PyTorch and Hugging Face. You can see more details and the training code here: https://github.com/kha-white/manga-ocr/tree/master/manga_ocr_dev