[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-detail:ZX20250601_78643814":3},{"code":4,"data":5},0,{"unicode":6,"title":7,"categoryId":8,"categoryName":9,"industryId":10,"industryName":11,"origin":12,"originAuthor":13,"originRemark":14,"originUrl":15,"pic":16,"content":17,"numRead":18,"numLike":4,"createTime":19,"hadFav":4,"hadLike":4,"status":4,"memberUnicode":20,"companyLogo":21,"companyName":22,"corporateVideoUrl":23,"collected":4,"corporate3dCover":24,"corporate3dUrl":25,"corporate3dId":26,"companyUnicode":27,"focusFlag":28,"exhibitionMainInfoVO":29},"ZX20250601_78643814","谷歌DeepMind最强AI手语翻译模型：SignGemma登场，打破手语沟通壁垒","1242381412612444162","行业动态","1245513623956107264","其它行业",1,"","http:\u002F\u002Ftech.ifeng.com\u002F","https:\u002F\u002Ftech.ifeng.com\u002Fc\u002F8jniL4kiTDg","https:\u002F\u002Fx0.ifengimg.com\u002Fucms\u002F2025_22\u002FB2FF9A29DD1FC0E038F6A96D206B7FA99C904185_size81_w1080_h1080.jpg","\u003Cdiv class=\"index_articleBox_6mBbT\" style=\"height:auto\">\n \u003Cdiv class=\"index_text_D0U1y\">\n  \u003Cp>IT之家 5 月 31 日消息，谷歌 DeepMind 团队于 5 月 27 日宣布推出 SignGemma，是其迄今为止最强大的手语翻译模型，可将手语转化为口语文本，该开源模型将于今年晚些时候加入 Gemma 模型家族。\u003C\u002Fp>\n  \u003Cp>\u003Cimg class=\"empty_bg\" src=\"https:\u002F\u002Fx0.ifengimg.com\u002Fucms\u002F2025_22\u002FB2FF9A29DD1FC0E038F6A96D206B7FA99C904185_size81_w1080_h1080.jpg\" src=\"data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQMAAAAl21bKAAAAA1BMVEXy8vJkA4prAAAACklEQVQI12NgAAAAAgAB4iG8MwAAAABJRU5ErkJggg==\" style=\" width: 640px; height: 640px;\">\u003C\u002Fp>\n  \u003Cp>IT之家注：SignGemma 模型支持多语言功能，但目前主要针对美国手语（ASL）和英语进行了深度优化，开源属性意味着开发者可以自由使用并改进它。\u003C\u002Fp>\n  \u003Cp>\u003Cimg class=\"empty_bg\" src=\"https:\u002F\u002Fx0.ifengimg.com\u002Fucms\u002F2025_22\u002F9E8BFC9B3A026BB35DC381E9467E9F05846A2FE8_size142_w900_h1689.jpg\" src=\"data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQMAAAAl21bKAAAAA1BMVEXy8vJkA4prAAAACklEQVQI12NgAAAAAgAB4iG8MwAAAABJRU5ErkJggg==\" style=\" width: 640px; height: 1201px;\">\u003C\u002Fp>\n  \u003Cp>DeepMind 希望通过这一技术，打破手语使用者在沟通上的障碍，让他们在工作、学习和社交中更顺畅地参与。\u003C\u002Fp>\n  \u003Cp>DeepMind 今年还推出 Gemma 3n 模型，支持从音频、图像、视频及文本输入生成智能文本，助力开发者打造实时互动应用。\u003C\u002Fp>\n  \u003Cp>此外，谷歌还与佐治亚理工学院及 Wild Dolphin Project 合作，推出 DolphinGemma 模型，分析并生成海豚声音，基于巴哈马大西洋斑点海豚的长期研究数据构建。\u003C\u002Fp>\n  \u003Cp>同时，MedGemma 模型作为 Gemma 3 家族新成员，聚焦医疗 AI，支持临床推理和医学影像分析，加速医疗与人工智能的融合创新。\u003C\u002Fp>\n \u003C\u002Fdiv>\n \u003Cspan>\u003C\u002Fspan>\n \u003Cdiv class=\"index_end_1O-ki\">\u003C\u002Fdiv>\n\u003C\u002Fdiv>",145,"2025-12-09 10:37:31","2299021137","https:\u002F\u002Fimages6396289.oss-accelerate.aliyuncs.com\u002F2299021137\u002F207k1en0gl\u002F39556b555c5294a73c851a6d064c914.png","云展 动力","https:\u002F\u002Fimages6396289.oss-accelerate.aliyuncs.com\u002F2299021137\u002Fow873ffgpa\u002F鸿威宣传视频.mp4","https:\u002F\u002Fimages6396289.oss-accelerate.aliyuncs.com\u002F2299021137\u002Fbx9hvodhys\u002F广州本部.jpg","https:\u002F\u002Fwww.ysdli.com\u002Fspc.html?m=luNgqWJZN","1405769664983003136","c99s2fxwoa6zj",-2,null]