Whale Call Detector

--- library_name: transformers license: bsd-3-clause base_model: MIT/ast-finetuned-audioset-10-10-0.4593 tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: whale-call-detector results: [] --- # whale-call-detector This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4111 - Accuracy: 0.8889 - Precision: 0.8947 - Recall: 0.8889 - F1: 0.9300 - F1 Water: 0.8 - F1 Resident: 0.9565 - F1 Transient: 0.9167 - F1 Humpback: 0.9167 - F1 Vessel: 0.75 - F1 Jingle: 0.8333 - F1 Human: 0.9412 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 0.1 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | F1 Water | F1 Resident | F1 Transient | F1 Humpback | F1 Vessel | F1 Jingle | F1 Human | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:--------:|:-----------:|:------------:|:-----------:|:---------:|:---------:|:--------:| | 0.5300 | 1.0 | 41 | 0.6064 | 0.8025 | 0.8245 | 0.8025 | 0.7915 | 0.8 | 0.8627 | 0.75 | 0.7619 | 0.7778 | 0.8333 | 0.75 | | 0.1062 | 2.0 | 82 | 0.5160 | 0.8765 | 0.8864 | 0.8765 | 0.8762 | 0.875 | 0.9020 | 0.8696 | 0.8571 | 0.8182 | 0.8333 | 0.9412 | | 0.0058 | 3.0 | 123 | 0.3918 | 0.9259 | 0.9316 | 0.9259 | 0.9215 | 0.9412 | 0.9388 | 0.9091 | 0.9167 | 0.9 | 0.8333 | 1.0 | | 0.0013 | 4.0 | 164 | 0.4327 | 0.8765 | 0.8832 | 0.8765 | 0.9020 | 0.8 | 0.9565 | 0.88 | 0.8696 | 0.75 | 0.8333 | 0.9412 | | 0.0008 | 5.0 | 205 | 0.4111 | 0.8889 | 0.8947 | 0.8889 | 0.9300 | 0.8 | 0.9565 | 0.9167 | 0.9167 | 0.75 | 0.8333 | 0.9412 | ### Framework versions - Transformers 5.10.2 - Pytorch 2.12.0+cu130 - Datasets 2.19.1 - Tokenizers 0.22.2