Models¶
Acoustic model V2.4 - June 2023¶
more than 6,000 species worldwide
covers frequencies from 0 Hz to 15 kHz with two-channel spectrogram (one for low and one for high frequencies)
0.826 GFLOPs, 50.5 MB as FP32
enhanced and optimized metadata model
global selection of species (birds and non-birds) with 6,522 classes (incl. 11 non-event classes)
Technical details¶
48 kHz sampling rate (we up- and downsample automatically and can deal with artifacts from lower sampling rates)
we compute 2 mel spectrograms as input for the convolutional neural network:
first one has fmin = 0 Hz and fmax = 3000; nfft = 2048; hop size = 278; 96 mel bins
second one has fmin = 500 Hz and fmax = 15 kHz; nfft = 1024; hop size = 280; 96 mel bins
both spectrograms have a final resolution of 96x511 pixels
raw audio will be normalized between -1 and 1 before spectrogram conversion
we use non-linear magnitude scaling as mentioned in Schlüter 2018
V2.4 uses an EfficienNetB0-like backbone with a final embedding size of 1024
See this comment for more details
Geo model (species range model) V2.4 - V2, Jan 2024¶
updated species range model based on eBird data
more accurate (spatial) species range prediction
slightly increased long-tail distribution in the temporal resolution
see this discussion post for more details
Acoustic model V3.0 (preview)¶
Note
The V3.0 acoustic model is currently a *preview* release (preview3.1) and may change before the final release.
global selection of more than 11,000 classes (birds and non-birds)
available in four backends, selectable via the
backendargument ofbirdnet.load:tf- TFLite/LiteRT (CPU only),fp32andfp16pb- ProtoBuf (CPU/GPU),fp32pt- PyTorch (CPU/GPU),fp32; requirespip install birdnet[pt]onnx- ONNX Runtime (CPU/GPU),fp32andfp16; requirespip install birdnet[onnx]
supports both
predict(..)andencode(..)on all backendsmultilingual common names in 30 languages
Technical details¶
32 kHz sampling rate (audio is automatically resampled)
3 s segments (96,000 samples) covering frequencies from 0 Hz to 15 kHz
final embedding size of 1280
import birdnet
# e.g. load the ONNX backend with FP16 precision
model = birdnet.load("acoustic", "3.0", "onnx", precision="fp16")
predictions = model.predict("example/soundscape.wav")
Geo model (species range model) V3.0¶
updated species range model covering more than 12,000 classes
aligned with the V3.0 acoustic taxonomy
available in two backends via the
backendargument ofbirdnet.load:tf- TFLite/LiteRT (CPU only),int8,fp16andfp32pb- ProtoBuf (CPU/GPU),fp32
import birdnet
model = birdnet.load("geo", "3.0", "tf")
predictions = model.predict(42.5, -76.45, week=4)
Using older models¶
Older models are not supported in the current version of the package. If you need to use an older model, please refer to the BirdNET-Analyzer repository.