Skip to content

Audio classification and event detection of natural audio recordings.

License

Notifications You must be signed in to change notification settings

filipmu/nature-audio-ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 

Repository files navigation

nature-audio-ai

Audio classification and event detection of natural audio recordings.

Read about SED (Sound Event Detection) here: https://www.kaggle.com/code/hidehisaarai1213/introduction-to-sound-event-detection/notebook - this was my starting point.

The series of notebooks with PANN-SED-1A all relate to the latest classification model which uses a modified version of the SED attention network here https://github.com/qiuqiangkong/audioset_tagging_cnn/

There is a notebook for training, prediction, and extracting features from the final linear layer. Training is based on the I am working on a clustering notebook.

Training is based on data from https://www.kaggle.com/competitions/birdclef-2021 along with other data. Format of data is similar to this contest data.

Other repos

About

Audio classification and event detection of natural audio recordings.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published