A deep learning project for bird audio classification using mel-spectrograms and convolutional neural networks. The model is trained on bird recordings from Poland, sourced from the GBIF Xeno-canto dataset, with support for data augmentation and class balancing.
Features
Mel-Spectrogram Processing: Converts audio waveforms to mel-spectrograms for deep learning
Data Augmentation: Time-shifting and volume adjustment for underrepresented classes
Stratified Dataset Splitting: 75% train, 15% validation, 10% test with balanced class distribution
Class Weighting: Handles class imbalance using weighted loss and balanced sampling
Comprehensive Metrics: Per-class accuracy, precision, recall, F1-score, and confusion matrix
Training Checkpoints: Save and resume training progress
Each folder represents a bird species (identified by GBIF taxonKey), containing 5-second audio clips in FLAC format.
Audio Processing Pipeline
Waveform Loading: Load audio files using torchaudio
Augmentation (training only):
Volume adjustment: ±6 dB random gain
Time-shifting: Up to 40% of audio length
Mel-Spectrogram Conversion:
FFT size: 2048
Mel bins: 128
Amplitude to dB with 80 dB top
Normalization: Global mean and standard deviation
Data Augmentation
Augmentation is selectively applied to classes with fewer than 500 samples during training.
Training
Prepare Dataset
First, prepare the dataset by running the data preparation pipeline to download and process audio files from GBIF. Then initialize the dataset for training:
Training Configuration
Optimizer: Adam (lr=0.0005, weight_decay=1e-4)
Scheduler: OneCycleLR (max_lr=0.001)
Loss: CrossEntropyLoss with class weights
Batch Size: 64
Sampler: WeightedRandomSampler for balanced batching
