Nemotron Speech Collection Open, state-of-the-art, productionβready enterprise speech models from the NVIDIA Speech research team for ASR, TTS, Speaker Diarization and S2S β’ 17 items β’ Updated 8 days ago β’ 34
Sleeping Featured 166 Kolors++ π 166 Generate images from prompts or images with enhanced captions
HuggingFaceTB/SmolVLM2-2.2B-Instruct Image-Text-to-Text β’ 2B β’ Updated Apr 8, 2025 β’ 174k β’ 299
Running 6 SmolVLM Realtime WebGPU (Vue) π 6 Yet another WebGPU based SmolVLM, re-implemented in Vue
SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System Paper β’ 2503.23108 β’ Published Mar 29, 2025 β’ 1