/datarmor-toolkit

This repo gathers all our analytical codes to process big (mostly audio) data (eg related to machine learning, ambient noise analysis…)

Primary LanguageJupyter Notebook

OSmOSE Project on Datarmor

The Open Science meets Ocean Sound Explorers is a collaborative research project aiming to develop a complete collection of FAIR acoustic analysis tools and methods.

Presentation

A toolkit has been deployed on the DATARMOR cluster of IFREMER, on which our production version runs. The toolkit is available to Datarmor members as a suite of notebooks covering basic processing cases:

  1. data_uploader.ipynb : used for the importation and formatting of a new dataset;

  2. spectrogram_generator.ipynb : used for the generation of file-scale (or shorter) spectrograms;

  3. soundscape_analyzer.ipynb : used for long-term analysis (i.e. with timescale at least longer than the audio file duration), including the computation of soundscape metrics (e.g. long-term averaged spectrograms, EPD) and the retrieval of raw welch spectra at different time resolutions;

Note : Steps 1 and 2 can be done for a batch of datasets at once using wrapper_data_uploader.ipynb and wrapper_spectrogram_generation.ipynb

See our user guide for more details.

License

This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. See LICENSE for the complete AGPL license