feat(transformers): add Nougat example

[hadipash]

Relies of PR #1271

Add:

• Nougat model example.

Usage:

from datasets import load_dataset
from transformers import NougatProcessor

from mindspore import tensor

from mindone.transformers import VisionEncoderDecoderModel

processor = NougatProcessor.from_pretrained("facebook/nougat-base")
model = VisionEncoderDecoderModel.from_pretrained("facebook/nougat-base")

# prepare PDF image for the model
dataset = load_dataset("hf-internal-testing/fixtures_docvqa")
image = dataset["test"][0]["image"].convert("RGB")
pixel_values = tensor(processor(image, return_tensors="np").pixel_values)

# generate transcription (here we only generate 30 tokens)
outputs = model.generate(
    pixel_values, min_length=1, max_new_tokens=30, bad_words_ids=[[processor.tokenizer.unk_token_id]]
)

sequence = processor.batch_decode(outputs, skip_special_tokens=True)[0]
sequence = processor.post_process_generation(sequence, fix_markdown=False)
print(sequence)

Performance:

The experiments were performed on Ascend Atlas 800T A2 hardware, utilizing MindSpore 2.6.0 in PyNative mode.

Model	Precision	Weight loading (s)	Speed
VisionEncoderDecoderModel	FP32	18	22 token/s

[gemini-code-assist]

Summary of Changes

Hello @hadipash, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates a practical example for the Nougat model, a Vision Transformer designed for Optical Character Recognition (OCR) of academic documents, into the mindone.transformers framework. The example provides a clear demonstration of how to use the model to convert PDF images into markdown text, enhancing accessibility to scientific knowledge. It serves as a valuable resource for developers looking to leverage Nougat's capabilities for document processing tasks.

Highlights

• New Nougat Model Example: This pull request introduces a new example for the Nougat model, demonstrating its usage for Optical Character Recognition (OCR) on scientific documents within the mindone.transformers library.
• Comprehensive Documentation: A README.md file has been added for the Nougat example, providing an overview of the model, its architecture, and detailed instructions on how to perform inference using NougatProcessor and VisionEncoderDecoderModel.
• Practical Usage Snippet: The example includes a Python code snippet that showcases how to load a dataset, preprocess an image, generate transcription, and post-process the output, making it easy for users to get started.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds a well-documented example for the Nougat model, including a README.md with an overview and usage instructions. The example is clear and helpful. My only suggestion is to include the performance metrics from the pull request description in the README.md to provide users with a more complete picture of the model's capabilities.

[gemini-code-assist]

This is a great example for the Nougat model. To make it even more complete, consider adding the performance metrics you've included in the pull request description to this README. This provides users with valuable information about the model's performance on specific hardware.

You can add the following section at the end of the file:

## Performance

The experiments were performed on Ascend Atlas 800T A2 hardware, utilizing MindSpore 2.6.0 in PyNative mode.

| Model                     | Precision | Weight loading (s) |   Speed    |
|---------------------------|:---------:|:------------------:|:----------:|
| VisionEncoderDecoderModel |   FP32    |         18         | 22 token/s |

[SamitHuang]

pls resolve linting errors