ONNX models for
Tara - browser-native visual document translation.
The original detector.onnx uses AveragePool with ceil_mode=1, which onnxruntime-web's WebGPU backend does not support. This repo hosts a patched version where ceil_mode is set to 0. Since all AveragePool nodes use kernel=2x2 stride=2 on even-dimension inputs (640x640), this change has no effect on output.
The LaMa inpainter works as-is and is included here for convenience (single download source).
These models are loaded by Tara via the browser Cache API. On first visit, the app downloads both models (~360 MB total) and caches them locally. Subsequent visits load from cache instantly.
Original models by
ogkalu. See the source repositories for license information.
