Hugging Face's logo
Jay's picture

Jay

ethereal-jay

AI & ML interests

None yet

Recent Activity

repliedto GoktugD's post about 23 hours ago
๐Ÿ‡น๐Ÿ‡ท 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: ๐Ÿ“„ 12 document categories ๐Ÿงช 72 held-out synthetic test pages ๐Ÿ“Š 0.15% average CER ๐Ÿ–ฅ๏ธ Fine-tuned on a single RTX 3090 ๐Ÿ”“ Apache 2.0 But here's what interests me more than another benchmark: Can the Hugging Face community find documents that break our model? ๐Ÿ”ฅ 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. ๐Ÿค— Model: https://huggingface.co/Werea-co/Werea-DocOCR-1B ๐Ÿ“š Dataset: https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 ๐Ÿ‡น๐Ÿ‡ท Built in Tรผrkiye. Open to everyone. Follow @GoktugD and @Werea-co to see the results of the challenge and our next experiments. ๐Ÿ’ฌ Question: What's the hardest document type you've ever tried to extract text from? #OCR #DocumentAI #OpenSourceAI #HuggingFace #TurkishAI
reacted to GoktugD's post with ๐Ÿ”ฅ about 23 hours ago
๐Ÿ‡น๐Ÿ‡ท 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: ๐Ÿ“„ 12 document categories ๐Ÿงช 72 held-out synthetic test pages ๐Ÿ“Š 0.15% average CER ๐Ÿ–ฅ๏ธ Fine-tuned on a single RTX 3090 ๐Ÿ”“ Apache 2.0 But here's what interests me more than another benchmark: Can the Hugging Face community find documents that break our model? ๐Ÿ”ฅ 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. ๐Ÿค— Model: https://huggingface.co/Werea-co/Werea-DocOCR-1B ๐Ÿ“š Dataset: https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 ๐Ÿ‡น๐Ÿ‡ท Built in Tรผrkiye. Open to everyone. Follow @GoktugD and @Werea-co to see the results of the challenge and our next experiments. ๐Ÿ’ฌ Question: What's the hardest document type you've ever tried to extract text from? #OCR #DocumentAI #OpenSourceAI #HuggingFace #TurkishAI
View all activity

Organizations

None yet