NAMAA-Space
/

Qari-OCR-0.1-VL-2B-Instruct

Image-Text-to-Text

Model card Files Files and versions

oddadmix commited on Mar 16

Commit

bd0e9ce

·

verified ·

1 Parent(s): 960646b

Update README.md

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -44,10 +44,14 @@ The model has been evaluated on standard OCR metrics, including Word Error Rate
 | Model | WER ↓ | CER ↓ | BLEU ↑ |
 |-------|-------|-------|--------|
-| Qari v0.1 Model | 0.068 | 0.019 | 0.860 |
-| Qwen2 VL 2B | 1.344 | 1.191 | 0.201 |
-| EasyOCR | 0.908 | 0.617 | 0.152 |
-| Tesseract OCR | 0.428 | 0.226 | 0.410 |
 ### Key Results

 | Model | WER ↓ | CER ↓ | BLEU ↑ |
 |-------|-------|-------|--------|
+| Qari-OCR-0.1-VL-2B-Instruct | 0.90 | 0.34 | 0.019 |
+| **Qari-OCR-0.2.2-Arabic-2B-Instruct** | **0.19** | **0.05** | **0.638** |
+| AIN 7B | 0.69 | 0.22 | 0.100 |
+| Qwen2-VL-2B-Instruct | 3.25 | 2.13 | 0.001 |
+| EasyOCR | 1.00 | 0.68 | 0.001 |
+| Tesseract | 0.99 | 0.94 | 0.000002 |
+*Note: For WER and CER, lower values are better (↓). For BLEU, higher values are better (↑).*
 ### Key Results