Demo for this model on Spaces
Hi @PaddlePaddle 🤗
I'm Apolinario, from the open-source team at Hugging Face. Congrats and thanks for open-sourcing PaddlePaddle/PP-OCRv6_medium_rec on the Hub! We were excited about this work and built with an agent an interactive demo app of it on Hugging Face Spaces, running on a free ZeroGPU infrastructure.
Here's a link to the demo: https://huggingface.co/spaces/hugging-apps/pp-ocrv6-medium-rec
We would love to transfer this demo to you or your organization. Would you like this demo to live under your own account or organization? If so just let me know here which username to transfer to, and we'll transfer the Space over to you, we hope it can give your work more visibility, discoverability and allows folks to try it out.
(If you have any questions or just want to chat more about this, you can find me on Twitter, LinkedIn or apolinario @ huggingface.co)
Cheers,
Poli
Hi Poli! Thank you so much for the incredible work and for putting this together!
Just to give a bit of context on the model architecture: PP-OCRv6_medium_rec is a recognition-only model, meaning it can rarely be used standalone and typically needs to be paired with PP-OCRv6_det (the detection model) to process full document images.
Because of this, we actually built an end-to-end pipeline app on ZeroGPU as well: https://huggingface.co/spaces/PaddlePaddle/PP-OCRv6_Online_Demo. It's a full-fledged demo that allows users to test the entire pipeline and toggle between different models.
Given that we already host this comprehensive demo, we probably won't be transferring your recognition-only Space under the official PaddlePaddle organization for now. Either way, we truly appreciate your amazing support and the effort you put into the Hugging Face community! Let’s definitely stay in touch.
Awesome! Thanks for creating that demo. It makes sense! I didn't catch it as the full fledged demo umbrella didn't have ZeroGPU tagged.
Thanks for open sourcing and let's definitely stay in touch
Thank you so much for your solid work. I am deeply moved to see that you personally made the demo for us. In addition, I will also be discussing some of the progress regarding Baidu's OCR-related work on X. Here is my account: https://x.com/slimcat0101, feel free to follow!
