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 2 days ago • 26
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 10 days ago • 471
Revisiting the Platonic Representation Hypothesis: An Aristotelian View Paper • 2602.14486 • Published 14 days ago • 11
Running on Zero MCP 1.02k Wan2.2 14B Preview 🐌 1.02k generate a video from an image with a text prompt
Running on Zero MCP Featured 80 BitDance-14B-64x 🚀 80 Open-source autoregressive model with binary visual tokens.
Running on Zero Featured 1.59k Qwen3-TTS Demo 🎙 1.59k Generate custom speech from text, voice descriptions, or samples
Running on Zero Featured 614 Wan 2 2 First Last Frame 💻 614 Generate a short video from a start and end image