mohajesmaeili/Qwen3-VL-2B-Persian-Arabic-Ocr-v1.0

Persian/Arabic OCR - Qwen3-VL-2B-Instruct - v1.0

This is a 16-bit version of Qwen/Qwen3-VL-2B-Instruct fine-tuned specifically for Persian text recognition (OCR) on individual text lines. The model has been trained exclusively on cropped single-line text images and is not designed for full-page OCR.

Training Details

• —Dataset:
• —56,000 real Persian text line images
• —100,000 synthetic images (47 fonts in 3 diffrent sizes) with clean and noisy/colored backgrounds
• —Total Examples: 156k text line images
• —Epochs: 1
• —LoRA Rank: 512
• —Batch Size: 100
• —Learning Rate: 2e-4
• —Trainable Parameters: 759M Params

Training Performance

Training loss decreased steadily, ending at approximately 0.071.