Alibaba unveils new AI model in Qwen series for multimodal processing

Posted under: AI technologies
Date: 2025-03-28
 Alibaba's Qwen2.5-Omni-7B Top Speech Recognition | Justo Global

Alibaba has unveiled Qwen2.5-Omni-7B, a new AI model capable of processing text, images, audio, and video while being efficient enough to run on mobile phones and laptops. The system excels particularly in speech understanding and generation. Now available on Hugging Face and GitHub, the model is designed to power AI agents that can assist visually impaired individuals through real-time audio descriptions. This release follows Alibaba's aggressive AI expansion strategy, which includes plans for significant investment in AI and cloud computing infrastructure.