From 1b9c352e55f5316586ad0b3378fd33864e81cd09 Mon Sep 17 00:00:00 2001 From: Perry Huang Date: Fri, 5 May 2023 08:29:20 -0700 Subject: [PATCH] Add TrOCR resources (#23142) * Add TrOCR resources * Made fixes suggested by stevhliu --- docs/source/en/model_doc/trocr.mdx | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/docs/source/en/model_doc/trocr.mdx b/docs/source/en/model_doc/trocr.mdx index 3e3a6c1007..8ad6566862 100644 --- a/docs/source/en/model_doc/trocr.mdx +++ b/docs/source/en/model_doc/trocr.mdx @@ -50,6 +50,27 @@ Tips: information, see the [official models](https://huggingface.co/models?other=trocr>). - TrOCR is always used within the [VisionEncoderDecoder](vision-encoder-decoder) framework. +## Resources + +A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with TrOCR. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource. + + + +- A blog post on [Accelerating Document AI](https://huggingface.co/blog/document-ai) with TrOCR. +- A blog post on how to [Document AI](https://github.com/philschmid/document-ai-transformers) with TrOCR. +- A notebook on how to [finetune TrOCR on IAM Handwriting Database using Seq2SeqTrainer](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/TrOCR/Fine_tune_TrOCR_on_IAM_Handwriting_Database_using_Seq2SeqTrainer.ipynb). +- A notebook on [inference with TrOCR](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/TrOCR/Inference_with_TrOCR_%2B_Gradio_demo.ipynb) and Gradio demo. +- A notebook on [finetune TrOCR on the IAM Handwriting Database](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/TrOCR/Fine_tune_TrOCR_on_IAM_Handwriting_Database_using_native_PyTorch.ipynb) using native PyTorch. +- A notebook on [evaluating TrOCR on the IAM test set](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/TrOCR/Evaluating_TrOCR_base_handwritten_on_the_IAM_test_set.ipynb). + + + +- [Casual language modeling](https://huggingface.co/docs/transformers/tasks/language_modeling) task guide. + +⚡️ Inference + +- An interactive-demo on [TrOCR handwritten character recognition](https://huggingface.co/spaces/nielsr/TrOCR-handwritten). + ## Inference TrOCR's [`VisionEncoderDecoder`] model accepts images as input and makes use of