transformers/docs/source/en/model_doc/nougat.md

Nougat

Overview

The Nougat model was proposed in Nougat: Neural Optical Understanding for Academic Documents by Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic. Nougat uses the same architecture as Donut, meaning an image Transformer encoder and an autoregressive text Transformer decoder to translate scientific PDFs to markdown, enabling easier access to them.

The abstract from the paper is the following:

Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural Optical Understanding for Academic Documents), a Visual Transformer model that performs an Optical Character Recognition (OCR) task for processing scientific documents into a markup language, and demonstrate the effectiveness of our model on a new dataset of scientific documents. The proposed approach offers a promising solution to enhance the accessibility of scientific knowledge in the digital age, by bridging the gap between human-readable documents and machine-readable text. We release the models and code to accelerate future work on scientific text recognition.

Nougat high-level overview. Taken from the original paper.

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

Tips:

• The quickest way to get started with Nougat is by checking the tutorial notebooks, which show how to use the model at inference time as well as fine-tuning on custom data.
• Nougat is always used within the VisionEncoderDecoder framework. The model is identical to Donut in terms of architecture.

Inference

Nougat's [VisionEncoderDecoder] model accepts images as input and makes use of [~generation.GenerationMixin.generate] to autoregressively generate text given the input image.

The [NougatImageProcessor] class is responsible for preprocessing the input image and [NougatTokenizerFast] decodes the generated target tokens to the target string. The [NougatProcessor] wraps [NougatImageProcessor] and [NougatTokenizerFast] classes into a single instance to both extract the input features and decode the predicted token ids.

• Step-by-step PDF transcription

>>> from huggingface_hub import hf_hub_download
>>> import re
>>> from PIL import Image

>>> from transformers import NougatProcessor, VisionEncoderDecoderModel
>>> from datasets import load_dataset
>>> import torch

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

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model.to(device)  # doctest: +IGNORE_RESULT

>>> # prepare PDF image for the model
>>> filepath = hf_hub_download(repo_id="hf-internal-testing/fixtures_docvqa", filename="nougat_paper.png", repo_type="dataset")
>>> image = Image.open(filepath)
>>> pixel_values = processor(image, return_tensors="pt").pixel_values

>>> # generate transcription (here we only generate 30 tokens)
>>> outputs = model.generate(
...     pixel_values.to(device),
...     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)
>>> # note: we're using repr here such for the sake of printing the \n characters, feel free to just print the sequence
>>> print(repr(sequence))
'\n\n# Nougat: Neural Optical Understanding for Academic Documents\n\n Lukas Blecher\n\nCorrespondence to: lblecher@'

See the model hub to look for Nougat checkpoints.

NougatImageProcessor

autodoc NougatImageProcessor - preprocess

NougatTokenizerFast

autodoc NougatTokenizerFast

NougatProcessor

autodoc NougatProcessor - call - from_pretrained - save_pretrained - batch_decode - decode - post_process_generation