翻译下面一段话为英文接下来让我们看下我们整个项目的进度以及整体的规划。整个项目分为三个阶段。在研究阶段我们研究了数字人的整体技术和驱动技术方向。并确定了我们的驱动技术方向。在面部驱动功能开发阶段我们的目标是使用音频驱动数字人类使他们能够展现逼真的面部表情。现在我们正处于面部驱动技术的发展阶段。接下来在身体驱动功能开发中我们还将使用音频来驱动逼真的数字人体动作。从下面的视频中我们可以看到面部捕捉技术

Next, let's take a look at the progress and overall planning of our entire project. The project is divided into three phases. In the research phase, we studied the overall technology and driving technology direction of digital humans, and determined our driving technology direction. In the facial driving function development phase, our goal is to use audio to drive digital humans to display realistic facial expressions. Currently, we are in the development phase of facial driving technology. Next, in the development of body driving functions, we will also use audio to drive realistic digital human body movements. From the video below, we can see that facial capture technology is now very mature. We only need an Apple device to capture the actor's facial movements and drive different 3D digital humans. Therefore, Apple devices can easily obtain data. The model we are currently developing can also use audio to drive the facial and head movements of digital humans to achieve realistic synchronization effects