Metadata-Version: 2.1
Name: hear-savi
Version: 0.0.1
Summary: An HEAR API for SAVI AudioCNN
Home-page: https://github.com/marl/hear-semav-embedding
Author: Sivan
Author-email: siwen.d@columbia.edu
License: LICENSE
Project-URL: Bug Tracker, https://github.com/marl/hear-semav-embedding/issues
Project-URL: Source Code, https://github.com/marl/hear-semav-embedding
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: librosa
Requires-Dist: typing
Requires-Dist: scikit-image
Requires-Dist: numba
Requires-Dist: numpy
Requires-Dist: torch
Requires-Dist: torchaudio (==0.11.0)
Provides-Extra: dev
Requires-Dist: pre-commit ; extra == 'dev'
Requires-Dist: black ; extra == 'dev'
Requires-Dist: pytest ; extra == 'dev'
Requires-Dist: pytest-cov ; extra == 'dev'
Requires-Dist: pytest-env ; extra == 'dev'
Provides-Extra: test
Requires-Dist: pytest ; extra == 'test'
Requires-Dist: pytest-cov ; extra == 'test'
Requires-Dist: pytest-env ; extra == 'test'

# HEAR-SAVI
This module extracts an audio subnetwork from the upstream semantic audio-visual navigation
([savi](https://github.com/marl/sound-spaces/tree/main/ss_baselines/savi)) model.

The embeddings implement the [common API](https://hearbenchmark.com/hear-api.html)
from HEAR Benchmark.

## Requirements
1. Install habitat-lab v0.2.1 and habitat-sim from commit 80f8e31140.
2. `pip install hear-savi`

````
@inproceedings{chen20soundspaces,
  title     =     {SoundSpaces: Audio-Visual Navigaton in 3D Environments},
  author    =     {Changan Chen and Unnat Jain and Carl Schissler and Sebastia Vicenc Amengual Gari and Ziad Al-Halah and Vamsi Krishna Ithapu and Philip Robinson and Kristen Grauman},
  booktitle =     {ECCV},
  year      =     {2020}
}
```
