PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks Paper • 2606.13108 • Published 15 days ago • 8
Running on Zero Agents 81 FamilyLegacy 📊 81 AI-driven voice cloning to preserve the voices of loved ones
Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks Paper • 2110.06525 • Published Feb 17, 2022 • 1
Running on CPU Upgrade Agents Featured 1.38k Open ASR Leaderboard 🏆 1.38k Explore and compare speech‑recognition model benchmarks
Running on Zero Agents Featured 260 MatchAnything 🏢 260 Find similar images and match them across collections
Running on Zero Agents Featured 112 Lance 🎬 112 Generate, edit, and understand images and videos with Lance!
Running on Zero Agents Featured 301 USO FLUX ⚡ 301 Generate custom images with style and subject references