Mert Kaya's picture
🀝 Open to Collab

Mert Kaya PRO

mertkayacs

AI & ML interests

Sr. AI Engineer, MSc & Sr. Fullstack Engineer Gen AI / XAI / CV / LLMs / Agentic Workflows TEDU MSc / TOBB ETU CS

Recent Activity

liked a model about 17 hours ago
RavichandranJ/Dolphin3-Cyber-8B-GGUF
reacted to GoktugD's post with πŸ”₯ 2 days ago
πŸ‡ΉπŸ‡· Our 1B Turkish OCR model achieved 0.15% character error rate. But there's a catch. That result came from a controlled evaluation. Real-world documents are a different challenge. Blurry phone photos. Damaged receipts. Complex tables. Handwritten annotations. Low-resolution scans. These are the cases where OCR systems can struggle. We built Werea-DocOCR-1B, an open-source model specialized for Turkish enterprise documents. Our published evaluation: πŸ“„ 12 document categories πŸ§ͺ 72 held-out synthetic test pages πŸ“Š 0.15% average CER πŸ–₯️ Fine-tuned on a single RTX 3090 πŸ”“ Apache 2.0 But here's what interests me more than another benchmark: Can the Hugging Face community find documents that break our model? πŸ”₯ THE TURKISH OCR CHALLENGE I'm looking for difficult Turkish documents that expose real weaknesses. If you work with OCR, document AI, or multilingual models, I'd love your input. We'll use the most interesting failure cases to improve our evaluations and share what we learn. No inflated claims. No hiding failures. Just open models and measurable progress. πŸ€— Model: https://huggingface.co/Werea-co/Werea-DocOCR-1B πŸ“š Dataset: https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 πŸ‡ΉπŸ‡· Built in TΓΌrkiye. Open to everyone. Follow @GoktugD and @Werea-co to see the results of the challenge and our next experiments. πŸ’¬ Question: What's the hardest document type you've ever tried to extract text from? #OCR #DocumentAI #OpenSourceAI #HuggingFace #TurkishAI
liked a model 2 days ago
deepseek-ai/DeepSeek-V4.1-Flash-1017
View all activity

Organizations

Eschatia Labs's profile picture