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 5 days ago • 26
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 13 days ago • 474
Revisiting the Platonic Representation Hypothesis: An Aristotelian View Paper • 2602.14486 • Published 16 days ago • 11
Running on Zero MCP 1.07k Wan2.2 14B Preview 🐌 1.07k generate a video from an image with a text prompt
Running on Zero MCP Featured 83 BitDance-14B-64x 🚀 83 Open-source autoregressive model with binary visual tokens.