Skip to content

A pipeline that transcribes audio to text using OpenAI's Whisper, extracts keywords with NLTK, and enables contextual keyword search via a Streamlit interface.

Notifications You must be signed in to change notification settings

Sivadharshini04/AudioScan

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

This web application transcribes the given audio of YouTube link/ audio file into text using Whisper ASR, extracts important keywords with NLTK, and allows contextual keyword search through an interactive Streamlit interface.

Features

  • Upload an YouTube link or an audio file
  • Full transcription display
  • Keyword frequency extraction
  • Keyword-in-Context (KWIC) search

Technologies Used

  • OpenAI Whisper
  • NLTK
  • Streamlit

About

A pipeline that transcribes audio to text using OpenAI's Whisper, extracts keywords with NLTK, and enables contextual keyword search via a Streamlit interface.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages