Qwen3 Voice Embedding Collection Standalone ECAPA-TDNN x-vector speaker encoders extracted from Qwen3-TTS. 1024-dim (0.6B) and 2048-dim (1.7B). • 4 items • Updated 15 days ago • 28
nvidia/diar_streaming_sortformer_4spk-v2 Automatic Speech Recognition • Updated Dec 31, 2025 • 22k • 108
Running on CPU Upgrade Featured 3.05k The Smol Training Playbook 📚 3.05k The secrets to building world-class LLMs