Skip to content

Fork for use by students at the TUB Advanced Projects Course.

deryaerman/Audio-Transcript-Anonymizer-TUB-AP

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Audio-Transcript-Anonymizer

This Pipeline accepts an audio or video file, transcribes the content using WhisperX and applies speaker diarization via Pyannote. It can be used for interviews, therapy sessions or conversations involving multiple speakers in general.

Features

Audio/video (mp3/mp4) input

Automatic transcription via WhisperX

Speaker diarization via Pyannote.audio

Installation

To run the transcription pipeline you'll need Python 3.10. and Anaconda.

  1. Installing FFmpeg

Option 1: Via pip

pip install python-ffmpeg

Option 2: Via scoop

scoop install ffmpeg
  1. Installing WhisperX

    Follow the instruction from the WhisperX repository (see 'Setup'):

    https://github.com/m-bain/whisperX?tab=readme-ov-file

  2. Installing Pyannote

Via Pip:

pip install pyannote.audio

Running the script

Place the script into a folder along with the subfolders 'audios' (for mp3) and/or 'videos' (for mp4) and add your media to the respective folder.

Open the script and update all fields marked with *** and save your changes. Run the script.

About

Fork for use by students at the TUB Advanced Projects Course.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%