Shruti Collection Offline speech to text, ~30 MB each, with English, in 22 languages: one small model per language. Phone, laptop, browser. • 23 items • Updated 15 days ago • 3
📡 Vela 3.0 Collection Six open routing models, 0.3B to 27B: the router's decisions and the spans you name, in one call. • 10 items • Updated 2 days ago • 15
Timestral Collection Time series foundation models for zero-shot probabilistic forecasting. • 4 items • Updated 30 days ago • 74
view article Article LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model lightonai • Oct 8 • 47
view article Article **Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization** nvidia • Sep 23 • 73
Holo1 Collection Vision-Language Action Model for use in Surfer-H web navigation agent • 6 items • Updated Sep 28 • 49
olmOCR Collection olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 12 items • Updated Dec 23, 2025 • 158
ZeroGPU Spaces Collection ZeroGPU Spaces made by the community • 17 items • Updated Jun 6, 2024 • 251
Notus 7B v1 Collection Notus 7B v1 models (DPO fine-tune of Zephyr SFT) and datasets used. More information at https://github.com/argilla-io/notus • 10 items • Updated Mar 2 • 19
Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning Paper • 2311.10709 • Published Nov 17, 2023 • 25
MusicGen Stereo Collection A collection of stereo music generation models as part of the v2 MusicGen release. • 4 items • Updated Apr 24, 2024 • 19