finanfa-ocr / config.json
Ronaldodev's picture
Initial release: Finanfa OCR - State of the Art Offline CPU Document Intelligence
a18d7f0 verified
Raw History Blame Contribute Delete
726 Bytes
{
"model_type": "finanfa-ocr",
"library": "finanfa-ocr",
"install": "pip install onnxruntime",
"framework": "onnxruntime",
"files": [
"det.onnx",
"lm.npz",
"lm_cjk.npz",
"lm_world.npz",
"math_dec_init.onnx",
"math_dec_step.onnx",
"math_enc.onnx",
"mathcls.onnx",
"meta.json",
"order.onnx",
"orient.onnx",
"rec.onnx",
"rec_cjk.onnx",
"rec_rtl.onnx",
"rec_world.onnx",
"script.onnx"
],
"note": "Finanfa OCR runs the .onnx files with onnxruntime. The .npz files are n-gram language models for unsure lines. model.safetensors holds the float weights of rec.onnx, the Latin-script recognizer, for the Hub parameter count; the package does not use it."
}