----------------------------------------------------------------------------------------------------
Program Author: Shakil Muhyiddin 

Technologies: Jupyter Notebook, ffmpeg library, AssemblyAI API

Purpose: The video audio transcription program is a software tool designed to automatically convert 
spoken words in a video into written text. Using advanced speech recognition algorithms, these programs 
analyze audio content, accurately transcribing dialogue, narration, and other audible elements. The 
resulting text can be crucial for various purposes, such as creating subtitles, improving accessibility 
for individuals with hearing impairments, and facilitating content searchability. This technology streamlines 
the process of converting spoken information from videos into a written format, saving time and effort for 
content creators and making multimedia content more accessible and versatile. 

Libraries and APIs:
<ffmpeg library>
    allows for video to audio conversions
<AssemblyAI API>
    processes audio into a transcription

Source Files:
<Video Audio Transcriptor.ipynb>

Launching instructions: each stage of the program can be easliy controlled by the user, even offering
different options when presenting the outputed transcription
----------------------------------------------------------------------------------------------------