Doa Model TL4

🚀 Sound Localisation Model

This model estimates the direction of arrival (DOA) from stational resound sources, trained and evaluated with a SOFA dataset and fine - tuned using the AST Model.

🚀 Quick Start

This section provides an overview of the Sound Localisation Model. It is designed to estimate the direction of arrival (DOA) from stational resound sources. The model was developed by leveraging a SOFA dataset for training and evaluation, and it was fine - tuned based on the AST Model (MIT/ast - finetuned - audioset - 10 - 10 - 0.4593).

📚 Documentation

Model Description

This is the model card for a Sound Localisation Model estimating the direction of arrival (DOA) from stational resound sources. The model was trained and evaluated using a SOFA dataset. This model was fine - tuned using the AST Model (MIT/ast - finetuned - audioset - 10 - 10 - 0.4593). Developed by Fidelis Odok (University of Hertfordshire).

📄 License

The model is under the creativeml - openrail - m license.