PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks Paper β’ 2606.13108 β’ Published Jun 11 β’ 8
Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks Paper β’ 2110.06525 β’ Published Feb 17, 2022 β’ 1
Running Agents 1.23k Edge TTS Text To Speech π 1.23k Generate speech audio from text with custom voice settings
Running on CPU Upgrade Agents Featured 1.4k Open ASR Leaderboard π 1.4k Explore and compare speech recognition model benchmarks
Running on Zero Agents Featured 259 MatchAnything π’ 259 Find similar images and match them across collections
Running on Zero Agents Featured 114 Lance π¬ 114 Generate, edit, and understand images and videos with Lance!
Running on Zero Agents Featured 301 USO FLUX β‘ 301 Generate custom images with style and subject references
Running on Zero Agents 228 MV Adapter I2MV SDXL π 228 Generate multi-view images from a single image