Modular Acoustic Detection

Environment Setup

To download all the relevant Ubuntu packages:

# Make script executable
$ chmod 777 ubuntu_packages_install.sh

# Run script to install
$ ./ubuntu_packages_install.sh

To load all git submodules:

$ git submodule update --init --recursive

To download all the data files:

# Make script executable
$ chmod 777 download_data_files.sh

$ ./download_data_files.sh

To download all the sound files (This is a really lengthy process and hence is not advisable unless you absolutely have to):

$ python download_all_sounds.py

Name		Name	Last commit message	Last commit date
Latest commit History 45 Commits
externals		externals
.gitignore		.gitignore
.gitmodules		.gitmodules
Download_SOI.py		Download_SOI.py
Explosions1.numbers		Explosions1.numbers
Generating_embeddings.py		Generating_embeddings.py
LICENSE		LICENSE
README.md		README.md
audioset_visualization.ipynb		audioset_visualization.ipynb
balancing_dataset.py		balancing_dataset.py
base_dataframe.py		base_dataframe.py
coarse_labels.pkl		coarse_labels.pkl
compare_vggish_out_vs_released_embedding.ipynb		compare_vggish_out_vs_released_embedding.ipynb
download_all_sounds.py		download_all_sounds.py
download_data_files.sh		download_data_files.sh
embeddings_column_to_base_df.py		embeddings_column_to_base_df.py
find_sounds.py		find_sounds.py
identify_silence.ipynb		identify_silence.ipynb
identifying_mislabelled_silence_audiofiles.py		identifying_mislabelled_silence_audiofiles.py
launch_jupyter_notebook.sh		launch_jupyter_notebook.sh
mislabelled_as_other_than_silence.txt		mislabelled_as_other_than_silence.txt
mislabelled_as_silent.txt		mislabelled_as_silent.txt
model_training.py		model_training.py
seperating_diff_sounds.py		seperating_diff_sounds.py
ubuntu_packages_install.sh		ubuntu_packages_install.sh
youtube_audioset.py		youtube_audioset.py