Skip to content

Instantly share code, notes, and snippets.

@hbredin

hbredin/AddNoiseFromGaps.ipynb

Created March 1, 2019 10:01
Show Gist options
  • Save hbredin/b15e3fd28f95b365250c8961bae45f68 to your computer and use it in GitHub Desktop.
Save hbredin/b15e3fd28f95b365250c8961bae45f68 to your computer and use it in GitHub Desktop.
Download ZIP
pyannote.audio.augmentation.noise
Display the source blob
Display the rendered blob
Raw
AddNoiseFromGaps.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@hbredin
Copy link
Author

hbredin commented Mar 1, 2019

To use this augmentation technique when training with pyannote.audio, one can simply use the following in config.yml:

data_augmentation:
   name: AddNoiseFromGaps
   params:
      snr_min: 10
      snr_max: 20
      protocol: Etape.SpeakerDiarization.TV
      subset: train

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment