Model files for the AI tools that run in the visitor's browser on freebiefy.com.

bg/isnet-general-use-w8.onnx
  Used by /tools/background-remover/.
  ISNet "general use" model from DIS (Highly Accurate Dichotomous Image Segmentation),
  Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, Luc Van Gool. https://github.com/xuebinqin/DIS
  License: Apache License 2.0 (see LICENSE-Apache-2.0.txt).
  Source: ONNX export isnet-general-use_1024.onnx (huggingface.co/jellybox/isnet-general-use, Apache 2.0).
  Changes: reduced to the final mask output,
  weights stored as 8 bit integers per output channel and dequantized to float32 when the model loads.
  Input 1x3x1024x1024 (RGB / 255 - 0.5), output 1x1x1024x1024.

tesseract/*.traineddata.gz
  Used by /tools/image-to-text/ with tesseract.js.
  Tesseract LSTM models (tessdata_best, integer version as packaged in @tesseract.js-data/<lang> 4.0.0_best_int).
  https://github.com/tesseract-ocr/tessdata_best
  License: Apache License 2.0 (see LICENSE-Apache-2.0.txt).

The ONNX Runtime Web and tesseract.js engine files are bundled from node_modules into /_astro/ at build time.