Add SPTSv2

[NielsRogge]

Model description

SPTSv2 is the latest SOTA text spotting model from Bytedance. Given that we already support DETR, should be a breeze to support this model as well.

SPTSv2 is an improvement over the first version: https://github.com/shannanyinxiang/SPTS.

Open source status

• [X] The model implementation is available
• [X] The model weights are available

Provide useful links for the implementation

https://github.com/bytedance/SPTSv2

[susnato]

Hi @NielsRogge can I please contribute this model?