الصفحة 1
الصفحة 1
Dream catcher
Dream Catcher is a video generation application that helps in many fields as science fiction, imagine event’s scenarios, education, animation and montage. By applying artificial algorithms implemented and trained on a dataset containing video samples and there descriptions to generate videos from any given text. The idea of generating videos from text is a new idea that was first presented at 2017, even that international companies like Google and OpenAi In the last year, was working on developing models to generate images from text. To make it easier to use the application, there are many ways to enter the text either by an image, voice or Typing from the keyboard.
Deep learning methods for converting speech to text = تقنيات التعلم العميق في تحويل الصوت إلى نص
Aims to design and develop a system capable of extracting audio content from films and audio recordings and converting it into text using deep learning techniques. This is done by analyzing audio patterns, extracting sounds and words from the video, and then converting them into written text. Deep learning, a branch of artificial intelligence, is used to accomplish this task. The study also includes comparing different deep learning techniques to determine their effectiveness in this context.
