docs: demo, experiments and live inference API on Tiyaro

[Venkat2811]

Motivation

Hello open-mmlab and mmocr team !

Thank you for your work on MMOCR. This project is interesting, and we think that it would be a great addition to make this great work instantly discoverable & available as an API for all your users, to quickly try and use it in their applications.

On Tiyaro, every model in MMOCR will get it’s own:

• Dedicated model card - Example: open-mmlab/mmocr/crnn_tps
• Model demo - Example: open-mmlab/mmocr/crnn_tps
• Unique Inference API - Example: open-mmlab/mmocr/crnn_tps
• Sample code snippets and swagger spec for the API

Users will also be able to compare your model with other models of similar types on various parameters using Tiyaro Experiments - Example: Text Recognition on MMOCR using IIIT 5k dataset

—-
I am from Tiyaro.ai. We are working on enabling developers to instantly evaluate, use and customize the world’s best AI. We are constantly working on adding new features to Tiyaro EasyTrain, EasyServe & Experiments, to make the best use of your ML model, and making AI more accessible for anyone.

Modification

Only README files are modified. badge is added.

BC-breaking (Optional)

• NIL -

Use cases (Optional)

• NIL -

Checklist

Before PR:

• I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
• Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
• Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
• New functionalities are covered by complete unit tests. If not, please add more unit test to ensure the correctness.
• The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

• If the modification has potential influence on downstream or other related projects, this PR should be tested with some of those projects.
• CLA has been signed and all committers have signed the CLA in this PR.

[CLAassistant]

All committers have signed the CLA.

[Venkat2811]

Hello @xinke-wang @Harold-lkk @gaotongxiao

Hope you are doing well. Looking forward to your PR review.

[gaotongxiao]

Hi, @Venkat2811! Thanks for your work in offering such a great AI platform! I can even see the full statistics of all the models in MMOCR, which must be backed by massive experiments and your team's unimaginable amount of effort.

But, before we make the decision, we are concerned about the way this project is maintained. Is it maintained by your team, by the community, or by some automatic scripts? Suppose we add a new model in the next release, how long would it take for Tiyaro to synchronize this update?

[Venkat2811]

Hello @gaotongxiao,

Thank you for your kind words and for your PR review ! Yes, indeed. We spent quite some time on collecting model stats for the MMOCR models.

• Since MMOCR is now a ‘native’ model on Tiyaro, the model onboarding and maintenance is done by Tiyaro Team.
• Model onboarding typically takes 2 days to 2 weeks.
• If you want the 2 day turnaround on model update you / any user can initiate a model onboarding request on Tiyaro Console using Tiyaro EasyServe. It's free and only signup is required.
• If you don't initiate the EasyServe request, then Tiyaro would typically pick up the new version in the next 2 weeks after it is released.