Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Rename charset.txt to charset.json

PP-OCRv6: XNNPACK detect is now static int8

Drop the pre-restructure flat artifacts

Re-export under the get_model_schema contract; restructure to the MODEL_SPEC layout

0.9.0

fixed the readmes

Upload 5 files

Update README.md

initial commit