Glimpse is a high-precision OCR model specialized for Right-to-Left (RTL) languages. It was developed as part of the ERNIE AI Developer Challenge 2025 to solve the "Script Bias" typically found in general-purpose vision models.
After 500 steps of fine-tuning, Glimpse achieved the following results on unseen RTL text lines:
This model was trained
2x faster using
Unsloth and Huggingface's TRL library. We utilized QLoRA (4-bit) to ensure efficient memory usage while maintaining high-fidelity weights.
