MSR-Codec: A Low-Bitrate Multi-Stream Residual Codec for High-Fidelity Speech Generation with Information Disentanglement Paper • 2509.13068 • Published Sep 16 • 1
view article Article From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages Feb 11 • 33
StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? Paper • 2510.02209 • Published Oct 2 • 53
Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices Paper • 2509.02523 • Published Sep 2 • 7
A Survey on Non-Intrusive ASR Refinement: From Output-Level Correction to Full-Model Distillation Paper • 2508.07285 • Published Aug 10 • 3
Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation Paper • 2501.15907 • Published Jan 27 • 17
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs Paper • 2503.01743 • Published Mar 3 • 89