Blagoj Mitrevski† • Arina Rak† • Julian Schnitzler† • Chengkun Li† • Andrii Maksai‡ • Jesse Berent • Claudiu Musat
† Joint first authors | ‡ Corresponding author
October 2024: We release Small-p on Hugging Face!
October 2024: Our work is now featured on the Google Research Blog!
February 2024: The InkSight Demo on Hugging Face is live!
To set up and run the Gradio Playground locally, you can use the following steps:
# Clone the huggingface spacegit clone https://huggingface.co/spaces/Derendering/Model-Output-Playground# Install the dependenciescd Model-Output-Playground pip install -r requirements.txt
Then you can run the following command to interact with the playground:
# Run the Gradio Playgroundpython app.py
Notice: Please use TensorFlow and tensorflow-text between version 2.15.0 and 2.17.0. Versions later than 2.17.0 may lead to unexpected behavior. We are currently investigating these issues.
We provide open resources for InkSight public version model. Choose the options that best fit your needs:
Public version model for CPU/GPU inference (494 MB)
Hugging Face model for CPU/GPU inference: InkSight Small-p.
Public version model for TPU inference (494 MB)
Supplementary material for the paper. This is used in the example colab linked below, which automatically downloads this content.
Example code in the form of a Colab notebook that showcases model inference results on several samples and example code to run the inference.
Samples of model outputs of huggingface demo.
The code in this repository is released under the Apache 2 license.
Please note: This is not an officially supported Google product.
If you find our work useful for your research and applications, please cite using this BibTeX:
@article{mitrevski2024inksight, title={InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write}, author={Mitrevski, Blagoj and Rak, Arina and Schnitzler, Julian and Li, Chengkun and Maksai, Andrii and Berent, Jesse and Musat, Claudiu}, journal={arXiv preprint arXiv:2402.05804}, year={2024}} 
