Hugging Face's logo
Mert Bozkurt's picture

Mert Bozkurt

mertbozkurt
2 10 83
99none99's profile picture umutkkgz's profile picture jadechoghari's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to savoji's post with 🔥 1 day ago
Idol, a new Apache-2.0 image-to-3D model from @speridlabs, makes a 3D Gaussian splat from one image in 7.2 GB of peak VRAM. It is the #1 trending model on the Hub with 1,057 likes. It writes a standard 3DGS .ply with up to 1,048,576 Gaussians, including sides the picture never showed, and does background removal and framing itself. The catch: the only quality evidence is the authors' own benchmark, on a repo created 2026-10-28. 📊 The numbers • Authors' benchmark, 1 x H100: best in 6 of 8 columns vs TripoSplat, TRELLIS and LGM (SSIM 0.726, LPIPS 0.213, DINOv2 0.781, CLIP 0.885) • LGM wins PSNR (12.46 vs 12.25) and speed (1.1 s). Idol takes 6.8 s vs 7.1 s for TRELLIS and 9.9 s for TripoSplat • 262,144 Gaussians, 50 steps: 3.4 s on B300, 6.7 s on H100, 19.1 s on RTX 4090, 46.2 s on a 10 GB RTX 3080 🛠️ Try it • Install idol-sdk, accept the terms of the gated DINOv3 and FLUX.2-dev models, run hf auth login • python -m idol.sample --image photo.jpg --mode real • --num_gaussians runs from 32,768 (0.4 MB) to 1,048,576 (12.2 MB) ⚠️ Caveats • Test set and size are not named, and no independent evaluation exists yet • The card says "under 2 seconds", but the timing table shows 3.4 s at best • Single objects only, NVIDIA CUDA required, no failure cases shown https://huggingface.co/speridlabs/idol https://speridlabs.com/research/idol If you run it on your own messy photos, how do the unseen sides hold up? 📚 Read it elsewhere • The deep dive on Medium: https://medium.com/p/5f660ae6ae56 • The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/speridlabs-idol-builds-3d-splats • The thread on X: https://x.com/saavoji/status/2119137739580858545 • Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#speridlabs-idol
reacted to GoktugD's post with 🔥 19 days ago
🇹🇷 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: 📄 12 document categories 🧪 72 held-out synthetic test pages 📊 0.15% average CER 🖥️ Fine-tuned on a single RTX 3090 🔓 Apache 2.0 But here's what interests me more than another benchmark: Can the Hugging Face community find documents that break our model? 🔥 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. 🤗 Model: https://huggingface.co/Werea-co/Werea-DocOCR-1B 📚 Dataset: https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 🇹🇷 Built in Türkiye. Open to everyone. Follow @GoktugD and @Werea-co to see the results of the challenge and our next experiments. 💬 Question: What's the hardest document type you've ever tried to extract text from? #OCR #DocumentAI #OpenSourceAI #HuggingFace #TurkishAI
liked a Space about 2 months ago
cihatyldz/divan-turkish-llm-arena
View all activity

Organizations

Hugging Face Context Course's profile picture