In this tutorial, we show how Whisper can be used with MoviePy to automatically generate and overlay translated subtitles from any video sample. We then walked through setting up this process to run both within a Notebook context and from an application served with Gradient Deployments.
In our newest article, we discuss autoencoders and convolutional autoencoders in the context of image data. We then show how to write custom autoencoders of our own with PyTorch, train them, and view our results in a Gradient Notebook.
In this blog post, we cover the three types of recommender systems, and demo their use with the MovieLens dataset.
In this article, we explore the whys and the hows behind the fundamental process of pooling in CNN architectures, and then compare two common techniques: max and average pooling.
In this blog, we show how to build an emoji suggestion system for short sentences rather than just a single word, and integrate it with a Flask interface.
In this tutorial, we walked through the capabilities and architecture of Open AI's Whisper, before showcasing two ways users can make full use of the model in just minutes with demos running in Gradient Notebooks and Deployments.
In this article, we compare and contrast various activation functions for deep learning with neural networks to try and determine the best class of these functions for different tasks.
In this article, we explore what global average and max pooling entail. We discuss why they have come to be used and how they measure up against one another. We also developed an intuition into why they work by performing a biopsy of our convnets and visualizing intermediate layers.
In this article, we demonstrate how to implement a version of a reinforcement learning technique Deep Q-Learning to create an AI agent capable of playing Checkers at a decent level.
