Skip to content

mportdata/newscast-transcriber

Repository files navigation

Uses Apache Beam to do the following in a way thats portable and can run in parallel: Import several frequently released newscasts (BBC, CNN, Fox etc.). For each newscast use OpenAI's Whisper model to create a transcript for further analysis.

About

Extract newscast transcriptions in parallel with Apache Beam and OpenAI's Whisper

Resources

Stars

Watchers

Forks

Packages

 
 
 

Contributors