Skip to content

Repository files navigation

beats_trainer: A high level API for training BEATs

BEATs (Bidirectional Encoder representation from Audio Transformers) is a powerful audio classification model that achieves state-of-the-art results. This library provides a streamlined API for training and using BEATs models on audio classification tasks.

✨ Key Features

  • 🤖 Automatic Checkpoint Management: Download BEATs models automatically
  • 🎵 Feature Extraction: Extract high-quality audio embeddings
  • 🔧 Simple Training API: Fine-tune BEATs with just a few lines of code
  • 🏗️ Train from Scratch: Initialize and train BEATs without pre-trained weights
  • � Long-Form Prediction: Process long audio files with timestamped predictions
  • �📚 Comprehensive Documentation: Step-by-step guides and examples
  • ⚡ GPU Support: Automatic CUDA detection and optimization

📖 Documentation

📜 License

MIT License. BEATs model weights are provided by Microsoft Research and OpenBEATs under their respective licenses.

🤝 Contributing

Contributions welcome! See our development setup guide.


Need help? Check the documentation or open an issue.

About

A high level interface for easily training BEATs, a powerful audio classification model

Resources

Stars

5 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages