Extracting the words from a video into a text document in Python using SpeechRecognition

By Divya Prackash Ravi

In this packet, the words used in a video is extracted by using moviepy and SpeechRecognition library available in Python and convert it into text document.

In this packet, we use the moviepy library to convert the video file into an audio file which will be used for recognization of the voices, and SpeechRecognition library to recognize the voices in the audio clip and converts them into text

Use this command below to install the packages

pip install SpeechRecognition moviepy

This is how your output folder will be like. The converted file is the audio file which was extracted by using moviepy library, the recognized text file is the output containing the words from the input video.

This is how the words from the video will be stored as in the text document