Update README.md

README.md

@@ -1,199 +1,265 @@
 ---
+pipeline_tag: image-text-to-text
 library_name: transformers
-tags: []
+language:
+- multilingual
+tags:
+- got
+- vision-language
+- ocr2.0
+license: apache-2.0
 ---
 
-# Model Card for Model ID
+<h1>General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model - HF Transformers 🤗 implementation
+</h1>
 
-<!-- Provide a quick summary of what the model is/does. -->
+[🤗 Spaces Demo](https://huggingface.co/spaces/yonigozlan/GOT-OCR-Transformers) | [🌟GitHub](https://github.com/Ucas-HaoranWei/GOT-OCR2.0/) | [📜Paper](https://arxiv.org/abs/2409.01704)</a> 
 
 
+[Haoran Wei*](https://scholar.google.com/citations?user=J4naK0MAAAAJ&hl=en), Chenglong Liu*, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu,  [Zheng Ge](https://joker316701882.github.io/), Liang Zhao, [Jianjian Sun](https://scholar.google.com/citations?user=MVZrGkYAAAAJ&hl=en), [Yuang Peng](https://scholar.google.com.hk/citations?user=J0ko04IAAAAJ&hl=zh-CN&oi=ao), Chunrui Han, [Xiangyu Zhang](https://scholar.google.com/citations?user=yuB-cfoAAAAJ&hl=en)
 
-## Model Details
 
-### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6653eee7a2d7a882a805ab95/QCEFY-M_YG3Bp5fn1GQ8X.jpeg)
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+Tips:
 
-### Model Sources [optional]
+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.
 
-<!-- Provide the basic links for the model. -->
+This model was contributed by [yonigozlan](https://huggingface.co/yonigozlan).
+The original code can be found [here](https://github.com/Ucas-HaoranWei/GOT-OCR2.0).
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## Usage example
 
-## Uses
+### Plain text inference
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+```python
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
 
-### Direct Use
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+>>> image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/image_ocr.jpg"
+>>> inputs = processor(image, return_tensors="pt").to(device)
 
-[More Information Needed]
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     max_new_tokens=4096,
+... )
 
-### Downstream Use [optional]
+>>> processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+"R&D QUALITY IMPROVEMENT\nSUGGESTION/SOLUTION FORM\nName/Phone Ext. : (...)"
+```
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Plain text inference batched
 
-[More Information Needed]
+```python
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
 
-### Out-of-Scope Use
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+>>> 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"
 
-[More Information Needed]
+>>> inputs = processor([image1, image2], return_tensors="pt").to(device)
 
-## Bias, Risks, and Limitations
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     max_new_tokens=4,
+... )
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+>>> processor.batch_decode(generate_ids[:, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
+["Reducing the number", "R&D QUALITY"]
+```
 
-[More Information Needed]
+### Formatted text inference
 
-### Recommendations
+GOT-OCR2 can also generate formatted text, such as markdown or LaTeX. Here is an example of how to generate formatted text:
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+```python
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
 
-## How to Get Started with the Model
+>>> 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)
 
-Use the code below to get started with the model.
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     max_new_tokens=4096,
+... )
 
-[More Information Needed]
+>>> 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\\) (...)"
+```
 
-## Training Details
+### Inference on multiple pages
 
-### Training Data
+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:
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-[More Information Needed]
+```python
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
 
-### Training Procedure
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+>>> 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)
 
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     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 processing A4-sized PDF pages. However, certain scenarios, like horizontally stitched two-page PDFs commonly found in academic papers or images with unusual aspect ratios, can lead to accuracy issues when processed as a single image. To address this, GOT can dynamically crop an image into patches, process them all at once, and merge the results for better accuracy with such inputs.
+Here is an example of how to process cropped patches:
+
+```python
+>>> import torch
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
+
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", torch_dtype=torch.bfloat16, device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
+
+>>> image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/one_column.png"
+>>> inputs = processor(image, return_tensors="pt", format=True, crop_to_patches=True, max_patches=3).to(device)
+
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     max_new_tokens=4096,
+... )
+
+>>> processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+"on developing architectural improvements to make learnable matching methods generalize.\nMotivated by the above observations, (...)"
+```
+
+### Inference on a specific region
+
+GOT supports 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. Here is an example of how to process a specific region:
+
+```python
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
+
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
+
+>>> image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/multi_box.png"
+>>> inputs = processor(image, return_tensors="pt", color="green").to(device) # or box=[x1, y1, x2, y2] for coordinates (image pixels)
+
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     max_new_tokens=4096,
+... )
+
+>>> processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+"You should keep in mind what features from the module should be used, especially \nwhen you’re planning to sell a template."
+```
+
+### Inference on general OCR data example: sheet music
+
+Although 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`.
+Here is an example of how to process sheet music:
+
+```python
+>>> from transformers import AutoProcessor, AutoModelForImageTextToText
+>>> import verovio
+
+>>> device = "cuda" if torch.cuda.is_available() else "cpu"
+>>> model = AutoModelForImageTextToText.from_pretrained("yonigozlan/GOT-OCR-2.0-hf", device_map=device)
+>>> processor = AutoProcessor.from_pretrained("yonigozlan/GOT-OCR-2.0-hf")
+
+>>> image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/sheet_music.png"
+>>> inputs = processor(image, return_tensors="pt", format=True).to(device)
+
+>>> generate_ids = model.generate(
+...     **inputs,
+...     do_sample=False,
+...     tokenizer=processor.tokenizer,
+...     stop_strings="<|im_end|>",
+...     max_new_tokens=4096,
+... )
+
+>>> outputs = processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+>>> tk = verovio.toolkit()
+>>> tk.loadData(outputs)
+>>> tk.setOptions(
+...     {
+...         "pageWidth": 2100,
+...         "pageHeight": 800,
+...         "footer": "none",
+...         "barLineWidth": 0.5,
+...         "beamMaxSlope": 15,
+...         "staffLineWidth": 0.2,
+...         "spacingStaff": 6,
+...     }
+... )
+>>> tk.getPageCount()
+>>> svg = tk.renderToSVG()
+>>> svg = svg.replace('overflow="inherit"', 'overflow="visible"')
+>>> with open("output.svg", "w") as f:
+>>>     f.write(svg)
+```
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/sheet_music.svg"
+alt="drawing" width="600"/>
+
+## Citation
+
+If you find our work helpful, please consider citing our papers 📝 and liking this project ❤️！
+
+```bib
+@article{wei2024general,
+  title={General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model},
+  author={Wei, Haoran and Liu, Chenglong and Chen, Jinyue and Wang, Jia and Kong, Lingyu and Xu, Yanming and Ge, Zheng and Zhao, Liang and Sun, Jianjian and Peng, Yuang and others},
+  journal={arXiv preprint arXiv:2409.01704},
+  year={2024}
+}
+@article{liu2024focus,
+  title={Focus Anywhere for Fine-grained Multi-page Document Understanding},
+  author={Liu, Chenglong and Wei, Haoran and Chen, Jinyue and Kong, Lingyu and Ge, Zheng and Zhu, Zining and Zhao, Liang and Sun, Jianjian and Han, Chunrui and Zhang, Xiangyu},
+  journal={arXiv preprint arXiv:2405.14295},
+  year={2024}
+}
+@article{wei2023vary,
+  title={Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models},
+  author={Wei, Haoran and Kong, Lingyu and Chen, Jinyue and Zhao, Liang and Ge, Zheng and Yang, Jinrong and Sun, Jianjian and Han, Chunrui and Zhang, Xiangyu},
+  journal={arXiv preprint arXiv:2312.06109},
+  year={2023}
+}
+```