├── .gitignore ├── LICENSE ├── README.md ├── assests ├── noises │ └── voices.wav ├── sed_result.png ├── test.mp3 ├── test.wav └── test2.wav ├── configs ├── audioset.yaml ├── audioset_sed.yaml ├── esc50.yaml ├── fsd2018.yaml └── scv1.yaml ├── datasets ├── __init__.py ├── audioset.py ├── aug_test.ipynb ├── esc50.py ├── fsdkaggle.py ├── speechcommands.py ├── transforms.py └── urbansound.py ├── models ├── __init__.py └── cnn14.py ├── requirements.txt ├── tools ├── infer.py ├── sed_infer.py ├── train.py └── val.py └── utils ├── __init__.py ├── losses.py ├── metrics.py ├── optimizers.py ├── schedulers.py ├── utils.py └── visualize.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/README.md -------------------------------------------------------------------------------- /assests/noises/voices.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/assests/noises/voices.wav -------------------------------------------------------------------------------- /assests/sed_result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/assests/sed_result.png -------------------------------------------------------------------------------- /assests/test.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/assests/test.mp3 -------------------------------------------------------------------------------- /assests/test.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/assests/test.wav -------------------------------------------------------------------------------- /assests/test2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/assests/test2.wav -------------------------------------------------------------------------------- /configs/audioset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/configs/audioset.yaml -------------------------------------------------------------------------------- /configs/audioset_sed.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/configs/audioset_sed.yaml -------------------------------------------------------------------------------- /configs/esc50.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/configs/esc50.yaml -------------------------------------------------------------------------------- /configs/fsd2018.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/configs/fsd2018.yaml -------------------------------------------------------------------------------- /configs/scv1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/configs/scv1.yaml -------------------------------------------------------------------------------- /datasets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/__init__.py -------------------------------------------------------------------------------- /datasets/audioset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/audioset.py -------------------------------------------------------------------------------- /datasets/aug_test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/aug_test.ipynb -------------------------------------------------------------------------------- /datasets/esc50.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/esc50.py -------------------------------------------------------------------------------- /datasets/fsdkaggle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/fsdkaggle.py -------------------------------------------------------------------------------- /datasets/speechcommands.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/speechcommands.py -------------------------------------------------------------------------------- /datasets/transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/transforms.py -------------------------------------------------------------------------------- /datasets/urbansound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/datasets/urbansound.py -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/models/__init__.py -------------------------------------------------------------------------------- /models/cnn14.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/models/cnn14.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/requirements.txt -------------------------------------------------------------------------------- /tools/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/tools/infer.py -------------------------------------------------------------------------------- /tools/sed_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/tools/sed_infer.py -------------------------------------------------------------------------------- /tools/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/tools/train.py -------------------------------------------------------------------------------- /tools/val.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/tools/val.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/losses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/utils/losses.py -------------------------------------------------------------------------------- /utils/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/utils/metrics.py -------------------------------------------------------------------------------- /utils/optimizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/utils/optimizers.py -------------------------------------------------------------------------------- /utils/schedulers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/utils/schedulers.py -------------------------------------------------------------------------------- /utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/utils/utils.py -------------------------------------------------------------------------------- /utils/visualize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sithu31296/audio-tagging/HEAD/utils/visualize.py --------------------------------------------------------------------------------