You can deploy this model and start earning money today!

davethaler/
whale-call-detector

Name: whale-call-detector
Availability: InStock

Views

No views yet

whale-call-detector

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

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: 23
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	F1 Water	F1 Resident	F1 Transient	F1 Humpback	F1 Vessel	F1 Jingle	F1 Human	F1 Bird
0.7812	1.0	46	0.5899	0.7826	0.7972	0.7826	0.7340	0.7619	0.84	0.6	0.7619	0.7	0.8	0.8182	0.9
0.1016	2.0	92	0.5209	0.8587	0.8817	0.8587	0.8723	0.7368	0.88	0.7368	1.0	0.72	0.8	1.0	0.9474
0.0088	3.0	138	0.3804	0.8804	0.8964	0.8804	0.9052	0.7619	0.9020	0.8571	0.9565	0.8	0.7273	1.0	0.9474
0.0016	4.0	184	0.3884	0.9130	0.9278	0.9130	0.9348	0.8182	0.9388	0.9091	0.9565	0.8	0.8	1.0	1.0
0.0008	5.0	230	0.3914	0.9239	0.9325	0.9239	0.9558	0.8571	0.9583	0.9091	1.0	0.8	0.8	0.9474	1.0