Downloads · 30 days
0
sceptre-zh_sim_g2
xberg-io/sceptre-zh_sim_g2
sceptre-zh_sim_g2 is a machine learning model from xberg-io. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for sceptre. The card lists the license as apache-2.0.
ONNX gen2 CRNN text recognizer for Simplified Chinese (6719 CTC classes). Part of sceptre, a Rust reimplementation of EasyOCR.
Access
Public
Updated Aug 8, 2026
Repo size
21.9 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx21.9 MB · 100%
At a glance
- Library
- sceptre
- License
- apache-2.0
- Access
- Public
- Created
- Aug 3, 2026
- Updated
- Aug 8, 2026
- SHA
- 81d76b3b
Model card
From the Hugging Face model README
Simplified Chinese gen2 recognizer (zh_sim_g2)
ONNX gen2 CRNN text recognizer for Simplified Chinese (6719 CTC classes). Part of sceptre, a Rust reimplementation of EasyOCR.
I/O contract
- Input:
[batch, 1, 64, width]f32, grayscale, height fixed at 64, dynamic batch and width. Normalize as(pixel/255 - 0.5) / 0.5before the model (not baked in). - Output:
[batch, time, num_classes]raw CTC logits (no softmax in the graph); class 0 is the CTC blank.
Attribution & license
Exported by the sceptre project from EasyOCR (Apache-2.0, JaidedAI). The underlying weights are JaidedAI's EasyOCR models; the ONNX export follows the lineage of the itextresearch/itext-EasyOCR-* exports.
Licensed under Apache-2.0, matching EasyOCR.
- Library
- sceptre
- License
- apache-2.0
- Created
- Aug 3, 2026
- Updated
- Aug 8, 2026