Downloads · 30 days
0
tara-models
QuatZo/tara-models
tara-models is a machine learning model from QuatZo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
ONNX models for Tara - browser-native visual document translation.
Access
Public
Updated Mar 28, 2026
Repo size
565 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx375 MB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026
- SHA
- c41c5939
Model card
From the Hugging Face model README
Tara Models
ONNX models for Tara - browser-native visual document translation.
Models
| Model | File | Size | Source | Changes |
|---|---|---|---|---|
| RT-DETR-v2 (detector) | detector.onnx | 161 MB | ogkalu/comic-text-and-bubble-detector | Patched AveragePool ceil_mode=0 for WebGPU compatibility |
| LaMa (inpainter) | lama-manga-dynamic.onnx | 197 MB | ogkalu/lama-manga-onnx-dynamic | No changes, original model |
Why this repo?
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).
Usage
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.
Direct download URLs:
- https://huggingface.co/QuatZo/tara-models/resolve/main/detector.onnx
- https://huggingface.co/QuatZo/tara-models/resolve/main/lama-manga-dynamic.onnx
License
Original models by ogkalu. See the source repositories for license information.
- License
- other
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026