— give Echo, our free transcription app powered by OpenAI’s Whisper, a try!<\/a><\/strong><\/em><\/p>\n <\/p>\n Times are moving fast in the machine learning space. Just a short while ago, OpenAI released Whisper<\/a>, a general-purpose speech recognition model. Not only did they open-source the model code<\/a>, they also provided the model weights, making it fully usable in just a few lines of Python. When I saw how simple the code snippet was to use Whisper, my immediate thought was to build an app with the model at its core. Below, I’ll show you how I used Lightning to deploy Whisper by OpenAI.<\/p>\n There are several audio\/video captioning services available, but most of them are proprietary and relatively expensive to use, charging upwards of $5\/minute of video, and more for languages other than English. Additionally, these services cannot be used for certain industries like healthcare and finance because of data security policies. This creates the perfect opportunity for a new app to disrupt this industry that can run using low-cost commodity GPUs and even in a private AWS account. So I pretended to be a startup company and set out to build an app!<\/p>\n My background is not<\/strong> in machine learning. I would call myself a full-stack developer who loves building end-to-end features using React. The Lightning Framework<\/a> looks and feels a lot like React, just written in Python, so it was very intuitive to learn and use as a backend for my transcription app. (You can look through Echo’s code here.<\/a>)<\/p>\n I decided to call my app Echo, after the Greek nymph<\/a> who was cursed to only repeat words that were spoken to her. Each piece of content that was transcribed would be turned into an \u201cEcho\u201d.<\/p>\n <\/p>\n <\/p>\n If you have worked at a startup before, you know that time is the most valuable resource. The faster you can take your great idea and turn it into a working prototype, the faster you can show it off to potential investors or customers.<\/p>\n With that in mind, our first goal was to validate that the Whisper model works and can be embedded into an app. The Whisper model runs much faster on a machine with a GPU. The Lightning Framework provides the perfect abstraction to run models and other compute-intensive workloads, called a \u201cWork\u201d<\/a> (. . .<\/h4>\n
Creating an App from a Model<\/h2>\n
LightningWork<\/code> in Python). All we need to do was to create a subclass of LightningWork<\/code> , and copy the Whisper sample code into its run()<\/code> method:<\/p>\n