acheamponge / Bundy-ML

A Speaker Diarization on Google Cloud machine learning project with Ted Bundy Audio Data

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Bundy-ML

A Speaker Diarization on Google Cloud machine learning project with Ted Bundy Audio Data

- Technologies Used

  • Jupyter Notebooks.
  • Python 3.7.1.
  • Pydub.
  • Google Cloud Speech To Text.

- Things Done

  • Scraped WAV audio files of interviews and court appearances of Ted Bundy during his trials.
  • Split the audio files into chunks with PyDub.
  • Converted stereo audio into mono audio files with PyDub.
  • Converted Speech To Text with Diarization with Google Cloud Speech-To-Text API.

About

A Speaker Diarization on Google Cloud machine learning project with Ted Bundy Audio Data


Languages

Language:Jupyter Notebook 100.0%