How to use from the
Use from the
Transformers library
# 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="Caraaaaa/text_image_captioning")
# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Caraaaaa/text_image_captioning")
model = AutoModelForImageTextToText.from_pretrained("Caraaaaa/text_image_captioning")
Quick Links

This is a GenerativeImage2Text model finetuned on non-text images extracted from documents (i.e.PDF). It is used to analyze the content of the image and produce a descriptive caption. It is part of a project to build a software solution capable of processing offline documents (PDFs, Word, PowerPoint, PPT, etc.) to detect WCAG accessibility issues.

Example document with non-text images: image/png Extracted Image: Alt text Generated caption: "Indication of correct signature"

Downloads last month
10
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train Caraaaaa/text_image_captioning