The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation Paper • 2606.20536 • Published Jun 18 • 13
MERIT: Learning Disentangled Music Representations for Audio Similarity Paper • 2605.27346 • Published May 26 • 8
Running on Zero MCP 1 Chatterbox Nano Demo ⚡ 1 Generate expressive speech from text with optional voice prompt
Configuration error Agents 22 SongFormer 🎵 22 State-of-the-art music analysis with multi-scale datasets
Running on Zero MCP 1 Chatterbox Nano Demo ⚡ 1 Generate expressive speech from text with optional voice prompt
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models Paper • 2603.25750 • Published Mar 20 • 36