None defined yet.
Team members 3
GirdAxe 's activityAll Models Datasets Spaces Buckets Papers Collections Community Posts Articles view post 🇹🇷 **A 1B Turkish OCR model vs. Baidu OCR.** We ran both models on the **same Turkish enterprise documents**. The result: **Werea-DocOCR-1B → 99.9** **Baidu Unlimited-OCR → 47.9** Same documents. Same evaluation. And Werea-DocOCR is only **1B parameters**. It was built specifically for difficult Turkish enterprise documents: 📄 invoices 📑 contracts 🏦 bank receipts 💼 payroll 🚗 vehicle documents 📋 SGK-style tables 📱 scanned & phone-captured documents But benchmarks aren't enough. **Give me a Turkish document that you think will break it.** We'll test the hardest ones and publish the failures. 🤗 Model: Werea-co/Werea-DocOCR-1B 📚 Dataset: Werea-co/werea-tr-doc-ocr-enterprise-v2 🇹🇷 Built in Türkiye. Open on Hugging Face. #OCR #DocumentAI #HuggingFace #TurkishAI See translation
view post 🇹🇷 **You tried to break our Turkish NER model.** And that's exactly what we wanted. After sharing Werea-TR-NER, we asked the Hugging Face community to challenge our ~110M parameter model with difficult Turkish sentences. Some worked. Some exposed weaknesses. And that's more valuable than pretending a benchmark score tells the whole story. Our published WikiANN-tr result: **91.7% Entity F1** 👤 PERSON → 94.2% 📍 LOCATION → 91.4% 🏢 ORGANIZATION → 89.2% But now we want to go further. 🔥 **ROUND 2** Send me a Turkish sentence designed specifically to break the model. Ambiguous names. Companies that sound like people. Locations hidden inside organization names. Turkish suffixes. Slang. Anything nasty. **Try to make it fail.** I'll collect the hardest examples and use them to build a public adversarial Turkish NER evaluation set. 🤗 Model: Werea-co/Werea-TR-NER 🇹🇷 Werea: Werea-co Follow me if you want to see whether the community can break it — and what we build from the failures. #TurkishNLP #HuggingFace #NER #OpenSourceAI See translation
view post 🇹🇷 **Can a 110M model understand Turkish names, places and organizations this well?** We tested Werea-TR-NER on the human-labeled WikiANN Turkish test set: **91.7% Entity F1** 👤 Person → **94.2%** 📍 Location → **91.4%** 🏢 Organization → **89.2%** Only ~110M parameters. Try it with a difficult Turkish sentence 👇 Ahmet Yılmaz İstanbul'da Werea şirketinde çalışıyor.→ Ahmet Yılmaz — PERSON → İstanbul — LOCATION → Werea — ORGANIZATION But easy examples are boring. **Give me the hardest Turkish sentence you can think of.** I'll run the most interesting ones through the model and share the failures too. 🤗 Model: Werea-co/Werea-TR-NER 🇹🇷 Werea: Werea-co **Follow Werea if you're interested in open Turkish AI — we're publishing the models, benchmarks and failures openly.** #TurkishNLP #HuggingFace #NER #OpenSourceAI See translation
view post 🇹🇷 One of our small Turkish models quietly reached **500+ monthly downloads** on Hugging Face. **Werea-TR-TextRestore — only 300M parameters.** Its job is simple: istanbulda hava cok guzel→ İstanbul'da hava çok güzel.A lightweight model for restoring Turkish text: • diacritics • punctuation • casing • corrupted text **96.5% word accuracy** on real Turkish news sentences. And it runs without sending your text to a cloud API. 🤗 Try the model: Werea-co/Werea-TR-TextRestore 🇹🇷 Built in Türkiye. Open source. If you're working on Turkish NLP, I'd love to hear what we should build next. #TurkishNLP #HuggingFace #OpenSourceAI #NLP See translation
2 replies · Reply view post 🇹🇷 We started with one question: **How much of the Turkish AI stack can we build openly?** Today, Werea has grown to **19 open models on Hugging Face.** Not just LLMs. 📄 Document AI — Werea-DocOCR-1B 🛡️ Cybersecurity — Werea-NanoSOC-8B 🔐 Privacy / KVKK — Werea-KVKK-Agent-4B 🔍 Retrieval — DUSUNEN-Rota-270M 🎙️ Speech — Werea-TSS 🧠 Turkish NLP — NER, NLI, QA, Intent, Sentiment, Topic & more 👁️ Computer Vision — Gemstone And we want the results to be measurable. Some of our published benchmarks: 🏷️ NER → **91.7% F1** — WikiANN-tr 🗂️ Topic → **92.8% accuracy** — TTC4900 🎯 Intent → **88.2% accuracy** — MASSIVE-tr 🧩 NLI → **74.5% accuracy** — XNLI-tr ❓ QA → **72.7% F1** — TQuAD2 📄 DocOCR → **0.15% CER** on our held-out Turkish enterprise document test Our goal isn't to upload as many models as possible. Our goal is to build an **open Turkish AI ecosystem**: Models. Datasets. Benchmarks. Demos. Real applications. Built from Türkiye. 🇹🇷 Open to everyone. 🤗 Explore Werea: Werea-co 📄 Document AI: Werea-co/Werea-DocOCR-1B 🛡️ NanoSOC: Werea-co/Werea-NanoSOC-8B 🔐 KVKK Agent: Werea-co/Werea-KVKK-Agent-4B 🔍 Rota: Werea-co/DUSUNEN-Rota-270M-v3 If you're building Turkish AI, follow Werea — there's much more coming. See translation
view post 🇹🇷 We trained a 1B OCR model specifically for Turkish enterprise documents. **Werea-DocOCR-1B v2** The result surprised us: LightOnOCR-2 base → **64.2% CER** Werea-DocOCR v1 → **~8.1% CER** Werea-DocOCR v2 → **0.15% CER** 🚀 Evaluated on a held-out 72-page test set across 12 Turkish document types and 3 different capture conditions. 📄 12 Turkish enterprise document types 🧪 12,960 synthetic training pages 📱 Digital + scanned + phone photos 📊 Tables → structured Markdown ⚙️ Full-parameter fine-tuning 🖥️ Trained on a single RTX 3090 It handles: • e-Invoices • rental contracts • bank receipts • payroll documents • insurance policies • vehicle documents • official correspondence • trade registry documents • SGK-style tables • and more. **Model 🤗** Werea-co/Werea-DocOCR-1B **Dataset 📚** Werea-co/werea-tr-doc-ocr-enterprise-v2 **Werea 🇹🇷** Werea-co We're building open AI models from Türkiye. This is just the beginning. #HuggingFace #OCR #DocumentAI #TurkishAI #OpenSourceAI #ComputerVision See translation
view post 🇹🇷 Introducing T3 Gemstone — Edge AI & Cybersecurity Models from Türkiye We've been building an open AI ecosystem focused on practical models that can run closer to the edge — not only in large datacenters. Today, I'm introducing T3 Gemstone, a growing family of compact AI models built around edge inference, cybersecurity and computer vision. 💎 T3 Gemstone currently includes: * NanoSOC Gemstone 2B — GGUF * NanoSOC Gemstone 4B — GGUF * Gemstone Person/Object Detector Nano * Edge-focused AI experiments and deployments The goal is simple: Build smaller, practical and open AI systems that can actually run on constrained hardware. This is part of a much larger open-source effort we're building from Türkiye across LLMs, cybersecurity, computer vision, retrieval, speech and edge AI. There is much more coming. 🤗 Explore my models, datasets and demos: @GoktugD 🛡️ NanoSOC: Werea-co/Werea-NanoSOC-8B Feedback, benchmarks, collaborations and contributions are very welcome. If you're interested inopen-source AI, Turkish AI research, edge AI or cybersecurity models, follow the journey. We're just getting started. 🇹🇷 #AI #OpenSource #HuggingFace #LLM #EdgeAI #Cybersecurity #ComputerVision #TurkishAI #MachineLearning See translation
