Renumics reposted this
Co-Founder at Renumics 🚀 | ML Engineer 🤖 | Writing about AI in engineering and manufacturing and interactive ML data visualization
The Audio Spectrogram Transformer (AST) outperforms traditional CNN-based methods, but it needs significantly more data. Additionally, the use of a pretrained model trained on internet data may not be suitable for your #industrial #AI use cases. 📖 In this tutorial https://lnkd.in/eaU8Q9_K, we show you how to use the SSAST (Self-Supervised Audio Spectrogram Transformer) framework to train a model on your own unlabeled data and convert it into an easy-to-use Hugging Face AST. For the conversion, a conversion script is used that maps the SSAST layer names to the corresponding Hugging Face layer names.