公众号:通义实验室(千问)📅 Jul 6AI 模型

Fun-ASR-Realtime 发布:单模型支持30种语言与16种方言,识别准确率领先

通义实验室发布Fun-ASR-Realtime实时语音识别模型。单模型覆盖30种语言及16种方言,针对东亚、东南亚地区重点优化。在工业级方言测评inhouse上取得87.8%的语义准确率,大幅领先,多地方言接近人工水平。引入上下文理解与动态热词注入,实现同音词、品牌名等语义消歧。流式识别首字延迟控制在百毫秒级,准确率接近离线水平,支持多语言无缝切换。API已上线阿里云百炼平台。

💡 Recommended AI Tools

The large video model released by Shengshu Technology and Tsinghua University supports highly consistent simulation of characters and physical laws.
The large video generation model launched by Kuaishou supports the generation of 1080p frame rate videos up to 2 minutes long.
ByteDance's AI painting and short video generation platform supports one-click text generation and shadow generation.
Tencent's official AI assistant deeply integrates WeChat public account ecology, search and file parsing capabilities.