Speech recognition allows software to recognize speech within audio and convert it into text. There are many interesting use-cases for speech recognition and it is easier than you may think to add it your own applications.
We just published a course on the freeCodeCamp.org YouTube channel that will teach you how to implement speech recognition in Python by building 5 projects.
Misra Turp & Patrick Loeber teach this course. Patrick is an experienced software engineer and Mirsra is an experienced data scientist. And they are both developer advocates at Assembly AI.
Assembly AI is a deep learning company that creates a speech-to-text API. You will learn how to use the API in this course. Assembly AI provided a grant that made this course possible.
In the first project you will learn the basics of audio processing by learning how to record audio from a microphone with pyaudio and write it to a wave file. You will also learn how to plot the sound waves with matplotlib.
In the second project you will learn how to implement simple speech recognition. You will learn how to use the AssemblyAI API and how to work with APIs with the requests module.
In the third project you will learn how to perform sentiment analysis on iPhone reviews from YouTube. You will learn how to use youtube-dl and how to implement sentiment classification.
In the fourth project you will write a program that will create automatic summarizations of podcasts using the Listen Notes API and Streamlit.
In the final project you will create a voice assistant with real-time speech recognition using websockets and the OpenAI API.
Watch the full course below or on the freeCodeCamp.org YouTube channel (2-hour watch).