Downloads · 30 days
0
bengali-ocr-detection
Sarjinkhan2003/bengali-ocr-detection
bengali-ocr-detection is a object detection model from Sarjinkhan2003. Use it when you need objects located in an image. The card lists the license as mit.
Architecture: YOLOv8n | Task: Word-level bounding box detection
Access
Public
Updated May 1, 2026
Repo size
80 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx12.4 MB · 54%
At a glance
- Task
- Object Detection
- License
- mit
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- May 1, 2026
- SHA
- b639c98b
Model card
From the Hugging Face model README
Bengali OCR — Word-Level Detection (v3)
Architecture: YOLOv8n | Task: Word-level bounding box detection
Results
| [email protected] | Precision | Recall |
|---|---|---|
| 0.9223 | 0.9533 | 0.8722 |
Training data
- ICDAR 2019 MLT Bengali (real word boxes)
- 6,000 synthetic printed pages (NID/form/paragraph style)
Usage
from ultralytics import YOLO
from huggingface_hub import hf_hub_download
path = hf_hub_download("Sarjinkhan2003/bengali-ocr-detection", "bengali_det.pt")
model = YOLO(path)
results = model.predict("doc.jpg", conf=0.25)
for box in results[0].boxes:
print(box.xyxy[0].tolist()) # one word per box
- Task
- Object Detection
- License
- mit
- Languages
- bn
- Created
- Apr 30, 2026
- Updated
- May 1, 2026