/google_speech_diarization_demo

A demo to show Speech Diarization (seperating audio of different speaker) and converting them to text using Google Cloud Speech API.

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

Google Speech Diarization

Prerequisites

You need Python 3.x.x for sure, and following libraries

  1. ffmpeg
  2. google-api-python-client
  3. tqdm
  4. httplib2
  5. oauth2client
  6. google-cloud-speech

How?

  1. Create Service account and get application credentials as JSON
  2. Get a sample mp3
  3. Replace dialog1.mp3 with your sample.mp3

Author

License

This project is licensed under the GNU General Public License v3.0 - see the LICENSE.md file for details