DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 β’ 15 items β’ Updated 4 days ago β’ 534
V-JEPA 2 Collection A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann β’ 8 items β’ Updated Jun 13, 2025 β’ 196
view post Post 14763 We did it. Kokoro TTS (v1.0) can now run 100% locally in your browser w/ WebGPU acceleration. Real-time text-to-speech without a server. β‘οΈGenerate 10 seconds of speech in ~1 second for $0.What will you build? π₯ webml-community/kokoro-webgpuThe most difficult part was getting the model running in the first place, but the next steps are simple:βοΈ Implement sentence splitting, allowing for streamed responsesπ Multilingual support (only phonemization left)Who wants to help? See translation 13 replies Β· π₯ 33 33 π 17 17 π 8 8 π€ 5 5 π 2 2 + Reply