【[30星]Baichuan-Omni-1.5：一个支持文本、图像、视频和音频输入以及文本和音频输出的开源全模态基础模型。亮点：1. 超强的视觉语言能力，平均得分73.3，比GPT-4o-mini高出6分；2. 统一且出色的语音能力，支持高质量的双语实时对话；3. 在医学图像理解方面表现卓越，OpenMM-Medical得分83.8%，超越Qwen2-VL-72B的80.7%】
'Baichuan-Omni-1.5 is the latest end-to-end trained omni-modal large model that supports comprehensive input modalities (text, image, video, audio) and dual output modalities (text and audio).'
GitHub: github.com/baichuan-inc/Baichuan-Omni-1.5
#全模态模型# #AI语音# #医学图像理解# #AI创造营#
'Baichuan-Omni-1.5 is the latest end-to-end trained omni-modal large model that supports comprehensive input modalities (text, image, video, audio) and dual output modalities (text and audio).'
GitHub: github.com/baichuan-inc/Baichuan-Omni-1.5
#全模态模型# #AI语音# #医学图像理解# #AI创造营#
