diff --git a/assets/writer.yaml b/assets/writer.yaml index f50caa93..265be323 100644 --- a/assets/writer.yaml +++ b/assets/writer.yaml @@ -141,3 +141,29 @@ financial professional for personal financial needs. monitoring: Unknown feedback: Downstream problems with this model should be reported to Hello@writer.com. +- type: model + name: GOT-OCR2_0 + organization: University of Chinese Academy of Sciences (ucaslcl) + description: This is a Unified End-to-end OCR model called GOT-OCR2_0. It can perform plain text OCR, formatted text OCR, and fine-grained OCR. It can also render its OCR results and perform multi-crop OCR. + created_date: 2024-09-28 + url: https://huggingface.co/stepfun-ai/GOT-OCR2_0 + model_card: https://huggingface.co/stepfun-ai/GOT-OCR2_0 + modality: + explanation: The inference section shows that it receives an image file as input and the output is plain, formatted or fine-grained OCR which are all text outputs. + value: image; text + analysis: Unknown + size: Unknown + dependencies: ['torch==2.0.1', 'torchvision==0.15.2', 'transformers==4.37.2', 'tiktoken==0.6.0', 'verovio==4.3.1', 'accelerate==0.28.0'] + training_emissions: Unknown + training_time: Unknown + training_hardware: Unknown + quality_control: Unknown + access: + explanation: The model can be accessed using the provided huggingface transformers code, implying it is openly accessible. + value: open + license: Unknown + intended_uses: The model is intended for OCR tasks including plain texts OCR, format texts OCR, and fine-grained OCR. It can also do multi-crop OCR and render its OCR results. + prohibited_uses: Unknown + monitoring: Unknown + feedback: Unknown +