nvidia/diar_streaming_sortformer_4spk-v2 Automatic Speech Recognition • Updated 4 days ago • 8.22k • 87
Running on Zero 4 GASM Enhanced - Geometric Language AI 🚀 4 Extract entities and relations from text for spatial analysis
Running Featured 350 Kokoro Text-to-Speech (WebGPU) 🗣 350 High-quality speech synthesis powered by Kokoro TTS
Running on Zero Featured 2.76k F5-TTS 🗣 2.76k F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)