GOT-OCR-2.0

🤗 Spaces Demo | 🌟GitHub | 📜Paper

Haoran Wei*, Chenglong Liu*, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, Chunrui Han, Xiangyu Zhang

Tips:

GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music. While this implementation of the model will only output plain text, the outputs can be further processed to render the desired format, with packages like pdftex, mathpix, matplotlib, tikz, verovio or pyecharts. The model can also be used for interactive OCR, where the user can specify the region to be recognized by providing the coordinates or the color of the region's bounding box.

This model was contributed by yonigozlan. The original code can be found here.

Usage example

Plain text inference

>>> from transformers import AutoProcessor, AutoModelForImageTextToText

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model = AutoModelForImageTextToText.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf", device_map=device)
>>> processor = AutoProcessor.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf")

>>> image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/image_ocr.jpg"
>>> inputs = processor(image, return_tensors="pt").to(device)

>>> generate_ids = model.generate(
...     **inputs,
...     do_sample=False,
...     tokenizer=processor.tokenizer,
...     stop_strings="",
...     max_new_tokens=4096,
... )

>>> processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
"R&D QUALITY IMPROVEMENT\nSUGGESTION/SOLUTION FORM\nName/Phone Ext. : (...)"

Plain text inference batched

>>> from transformers import AutoProcessor, AutoModelForImageTextToText

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model = AutoModelForImageTextToText.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf", device_map=device)
>>> processor = AutoProcessor.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf")

>>> image1 = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/multi_box.png"
>>> image2 = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/image_ocr.jpg"

>>> inputs = processor([image1, image2], return_tensors="pt").to(device)

>>> generate_ids = model.generate(
...     **inputs,
...     do_sample=False,
...     tokenizer=processor.tokenizer,
...     stop_strings="",
...     max_new_tokens=4,
... )

>>> processor.batch_decode(generate_ids[:, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
["Reducing the number", "R&D QUALITY"]

Formatted text inference

GOT-OCR2 can also generate formatted text, such as markdown or LaTeX. Here is an example of how to generate formatted text:

>>> from transformers import AutoProcessor, AutoModelForImageTextToText

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model = AutoModelForImageTextToText.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf", device_map=device)
>>> processor = AutoProcessor.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf")

>>> image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/latex.png"
>>> inputs = processor(image, return_tensors="pt", format=True).to(device)

>>> generate_ids = model.generate(
...     **inputs,
...     do_sample=False,
...     tokenizer=processor.tokenizer,
...     stop_strings="",
...     max_new_tokens=4096,
... )

>>> processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
"\\author{\nHanwen Jiang* \\(\\quad\\) Arjun Karpur \\({ }^{\\dagger} \\quad\\) Bingyi Cao \\({ }^{\\dagger} \\quad\\) (...)"

Inference on multiple pages

Although it might be reasonable in most cases to use a “for loop” for multi-page processing, some text data with formatting across several pages make it necessary to process all pages at once. GOT introduces a multi-page OCR (without “for loop”) feature, where multiple pages can be processed by the model at once, whith the output being one continuous text. Here is an example of how to process multiple pages at once:

>>> from transformers import AutoProcessor, AutoModelForImageTextToText

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model = AutoModelForImageTextToText.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf", device_map=device)
>>> processor = AutoProcessor.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf")

>>> image1 = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/page1.png"
>>> image2 = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/page2.png"
>>> inputs = processor([image1, image2], return_tensors="pt", multi_page=True, format=True).to(device)

>>> generate_ids = model.generate(
...     **inputs,
...     do_sample=False,
...     tokenizer=processor.tokenizer,
...     stop_strings="",
...     max_new_tokens=4096,
... )

>>> processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
"\\title{\nGeneral OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model\n}\n\\author{\nHaoran Wei (...)"

Inference on cropped patches

GOT supports a 1024×1024 input resolution, which is sufficient for most OCR tasks, such as scene OCR or processin