v0.7.1

OpenSoundscape v0.7.1

This release updates dependencies, fixes various bugs, updates documentation, and adds a few small features.

Notable feature additions

• Parsing metadata from AudioMoth firmware through 1.8.1 and from SongMeter Micros is now supported. The Audio.from_file method will automatically parse metadata and store it in the object's .metadata dictionary unless you specify metadata=False
• Audio.save() now saves metadata, so that you can retain or update .wav file metadata when using OpenSoundscape
• ResNet networks with pre-trained weights and a number of input channels other than 3 now average conv1 weights over the input channels

Dependencies

Python 3.9 no longer causes installation issues. This release updates OpenSoundscape's package dependencies in a way that allows Python 3.9 environments. Users with Apple Silicon chips to install OpenSoundscape hassle-free in a Python 3.9 environment (but may experience issues with Python 3.7 and 3.8).

If you encounter problems with installation, regardless of your platform, please open an issue.

What's Changed: a list of merged Pull Requests

• add scaling option to the Spectrogram class and MelSpectrogram class by @zoharrpg in #505
• Annotation docs hotfix by @rhine3 in #517
• Minor updates to annotation tutorial by @rhine3 in #516
• Fixes Poetry Installer issue during CI by @louisfh in #535
• change filepath of poetry by @louisfh in #536
• Removed redundant empty load method from base model modules by @jatinkhilnani in #537
• Update black version by @sammlapp in #539
• Issue 472 spectrogram methods by @louisfh in #534
• Resolved - Resample with replacement #479 by @jatinkhilnani in #497
• resolve 520 skip loading metadata by @sammlapp in #541
• resolve 513 Spectrogram loses properties on out-of-place method by @sammlapp in #542
• Fix loading of ResampleLoss CNN models by @sammlapp in #544
• Resolve Issue 507 metrics by @sammlapp in #540
• update pre-commit black version to 22.8.0 by @sammlapp in #551
• Issue 531 final clip by @jatinkhilnani in #550
• Issue 496 tests for cnn arch by @louisfh in #545
• different # input channels should retain pre-trained weights by @sammlapp in #546
• Issue #523 AudioMoth 1.5-1.8.1 MetaData by @syunkova in #553
• Sammlapp/issue391 by @sammlapp in #554
• v0.7.1 by @sammlapp in #557

New Contributors

• @zoharrpg made their first contribution in #505
• @syunkova made their first contribution in #553

Full Changelog: v0.7.0...v0.7.1