Hugging Face's logo
hakan g's picture

hakan g

hgner
4
Β·

AI & ML interests

None yet

Recent Activity

reacted to GoktugD's post with ❀️ 2 days ago
πŸ‡ΉπŸ‡· We trained a 1B OCR model specifically for Turkish enterprise documents. **Werea-DocOCR-1B v2** The result surprised us: LightOnOCR-2 base β†’ **64.2% CER** Werea-DocOCR v1 β†’ **~8.1% CER** Werea-DocOCR v2 β†’ **0.15% CER** πŸš€ Evaluated on a held-out 72-page test set across 12 Turkish document types and 3 different capture conditions. πŸ“„ 12 Turkish enterprise document types πŸ§ͺ 12,960 synthetic training pages πŸ“± Digital + scanned + phone photos πŸ“Š Tables β†’ structured Markdown βš™οΈ Full-parameter fine-tuning πŸ–₯️ Trained on a single RTX 3090 It handles: β€’ e-Invoices β€’ rental contracts β€’ bank receipts β€’ payroll documents β€’ insurance policies β€’ vehicle documents β€’ official correspondence β€’ trade registry documents β€’ SGK-style tables β€’ and more. **Model πŸ€—** https://huggingface.co/Werea-co/Werea-DocOCR-1B **Dataset πŸ“š** https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 **Werea πŸ‡ΉπŸ‡·** https://huggingface.co/Werea-co We're building open AI models from TΓΌrkiye. This is just the beginning. #HuggingFace #OCR #DocumentAI #TurkishAI #OpenSourceAI #ComputerVision
published a bucket 19 days ago
hgner/model-trajectories-bucket
updated a bucket 19 days ago
hgner/UI-Elements-Detection-Dataset-bucket
View all activity

Organizations

None yet