据VentureBeat报道，Reka公司推出了一款名为Yasa-1的多模态人工智能助手。这款人工智能初创公司由DeepMind、谷歌、百度和Meta的研究人员创立。Yasa-1不仅能够理解文本，还能理解图像、短视频和音频片段。
Yasa-1是一款多模态人工智能助手，它能够同时处理文本和图像等多种类型的数据。它可以识别语音中的单词，提取文本中的实体，识别图像中的物体和场景，并理解视频中的动作和情感。Yasa-1的推出，标志着人工智能技术在多模态处理方面取得了重大突破。
目前，Yasa-1已经可以识别超过20种语言中的实体，并支持实时语音翻译。它还可以识别不同人声中的说话人，并提供相应的语音反应。Yasa-1的多模态处理能力，使其在智能客服、智能家居、智能医疗等领域有着广泛的应用前景。
虽然目前Yasa-1仍处于测试阶段，但它的推出已经引起了业界的高度关注。随着Yasa-1的正式推出，人工智能技术将进一步提升，推动多模态数据处理技术的发展。
新闻翻译：
Title: Reka’s Yasa-1: A Multi-modal Artificial Intelligence Assistant
Keywords: Multi-modal, artificial intelligence, assistant, Yasa-1
Text:
According to VentureBeat, Reka has launched a multi-modal artificial intelligence assistant called Yasa-1. The startup, founded by researchers from DeepMind, Google, Baidu, and Meta, can understand both text and images, as well as audio and video clips.
Yasa-1 is a multi-modal artificial intelligence assistant that can handle both text and image data at the same time. It can recognize words in speech, extract entities in text, recognize objects and scenes in images, and understand actions and emotions in videos. The launch of Yasa-1 marks a significant breakthrough in multi-modal processing technology.
Currently, Yasa-1 can recognize more than 20 languages for entity recognition and support real-time voice translation. It can also recognize different speakers in voice and provide corresponding audio responses. Yasa-1’s multi-modal processing capabilities make it promising for applications in intelligent customer service, smart homes, smart medical care, and more.
Although Yasa-1 is currently in the testing phase, its launch has attracted a lot of attention in the industry. With the official release of Yasa-1, artificial intelligence technology will further improve, and multi-modal data processing technology will advance.
【来源】https://venturebeat.com/ai/reka-launches-yasa-1-a-multimodal-ai-assistant-to-take-on-chatgpt/
Views: 1