ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark Paper โข 2507.05727 โข Published Jul 8, 2025 โข 1
Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 โข 6 items โข Updated Mar 2 โข 168