Audio or acoustic sound is all around us, it can be generated by machinery in a factory, a living animal, or human with flu like symptoms such as sneeze and cough. When sufficient audio data is collected, it can be put into use with machine learning to do anomaly detection and classification.
In this example, the model take reference to the paper Very Deep Convolutional Neural Networks for Raw Waveforms by Wei Dai et al., you can get more information by reading the paper.
The objective of this post is to demonstrate audio classification using SageMaker PyTorch framework which can be easily modified to suit different use cases.
- UrbanSound8k
- Building acoustic classification model using PyTorch
- Building a custom container on SageMaker PyTorch Deep Learning Framework
- Run PyTorch training job using SageMaker script mode
- Deploy custom model using default SageMaker PyTorch container for inference
This is tested on sagemaker==1.64.1
This library is licensed under the MIT-0 License. See the LICENSE file.