Birdnet

Latest version: v0.1.7

Safety actively analyzes 722491 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 2

0.2.1

- install the TensorFlow Metal Plugin for GPU support on Apple devices 25
- optionally use Apache Arrow to improve performance by reducing memory usage during data conversion and minimizing data
copying between R and Python. 26

0.2.0

This update brings significant changes and improvements, including support for loading pre-existing and custom-trained models, aligning the package with birdnet `0.1.6`.

breaking changes:
- The `init_model()` function is now **deprecated** and will be removed in the next version. Please use the `birdnet_model_*` function family for model initialization.
- `available_languages()` **update**: A new argument has been added to `available_languages()` to specify the BirdNET version, making it more flexible for different model versions.
- **Renaming** `get_labels_path` to `labels_path()`. It now requires a model object as its first argument.
- `predict_species()` was **renamed** to `predict_species_from_audio_file()`
- `predict_species_at_location_and_time()` was **changed** to requirer a model object as first argument.

New features:
* **Support for Custom Models:** You can now load custom-trained models
* **A new set of functions** (`birdnet_model_*`) to load pre-existing and custom-trained models. These functions offer a more flexible approach to model loading. See `?birdnet_model_load` for more details.
* **S3 Object-Oriented System:** The models are now implemented as S3 classes, and most of the functionality related to these models is provided through methods. This update makes the API cleaner and more consistent, and allows for better extensibility in future versions.

0.1.7

Changed

- Switched model download links from TUCcloud to Zenodo [10](https://github.com/birdnet-team/birdnet/issues/10)

Fixed

- Added check for mono files [9](https://github.com/birdnet-team/birdnet/issues/9)

0.1.6

Added

- Support for multiprocessing using `predict_species_within_audio_files_mp`

Changed

- Separate `ModelV2M4TFLite` into `AudioModelV2M4TFLite` and `MetaModelV2M4TFLite`
- Separate `ModelV2M4Protobuf` into `AudioModelV2M4Protobuf` and `MetaModelV2M4Protobuf`
- Separate `ModelV2M4` into `AudioModelV2M4` and `MetaModelV2M4`
- Move v2.4 models to `birdnet.models.v2m4`
- Yield results of `predict_species_within_audio_file` instead of returning an OrderedDict
- Extracted method `predict_species_within_audio_file` and `predict_species_at_location_and_time` from their respective model
- set default value for `batch_size` to 100

0.1.5

0.1.4

Page 1 of 2

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.