├── .gitignore ├── LICENSE ├── README.md ├── config.py ├── data_util ├── audioset_classes.py ├── audioset_strong.py ├── dcase2016task2.py └── transforms.py ├── ex_audioset_strong.py ├── ex_dcase2016task2.py ├── helpers ├── augment.py ├── decode.py ├── encode.py ├── score.py └── utils.py ├── hf_dataset_gen ├── audioset_strong.py └── metadata │ ├── audioset_eval_strong.csv │ ├── audioset_train_strong.csv │ ├── class_labels_indices.csv │ └── class_labels_indices_strong.csv ├── images └── downstream_task_results.png ├── inference.py ├── models ├── asit │ ├── ASIT_wrapper.py │ ├── data_transformations.py │ ├── utils.py │ └── vision_transformer.py ├── atstframe │ ├── ATSTF_wrapper.py │ ├── audio_transformer.py │ └── transformer.py ├── beats │ ├── BEATs.py │ ├── BEATs_wrapper.py │ ├── Tokenizers.py │ ├── backbone.py │ ├── modules.py │ └── quantizer.py ├── frame_mn │ ├── Frame_MN_wrapper.py │ ├── block_types.py │ ├── model.py │ └── utils.py ├── frame_passt │ ├── fpasst.py │ ├── fpasst_wrapper.py │ ├── preprocess.py │ └── vit_helpers.py ├── m2d │ ├── M2D_wrapper.py │ └── portable_m2d.py ├── prediction_wrapper.py ├── seq_models.py └── transformer_wrapper.py ├── requirements.txt ├── resources ├── README.md └── eval_durations.csv └── test_files ├── 752547__iscence__milan_metro_coming_in_station.wav └── freesound_attributions.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/README.md -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/config.py -------------------------------------------------------------------------------- /data_util/audioset_classes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/data_util/audioset_classes.py -------------------------------------------------------------------------------- /data_util/audioset_strong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/data_util/audioset_strong.py -------------------------------------------------------------------------------- /data_util/dcase2016task2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/data_util/dcase2016task2.py -------------------------------------------------------------------------------- /data_util/transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/data_util/transforms.py -------------------------------------------------------------------------------- /ex_audioset_strong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/ex_audioset_strong.py -------------------------------------------------------------------------------- /ex_dcase2016task2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/ex_dcase2016task2.py -------------------------------------------------------------------------------- /helpers/augment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/helpers/augment.py -------------------------------------------------------------------------------- /helpers/decode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/helpers/decode.py -------------------------------------------------------------------------------- /helpers/encode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/helpers/encode.py -------------------------------------------------------------------------------- /helpers/score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/helpers/score.py -------------------------------------------------------------------------------- /helpers/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/helpers/utils.py -------------------------------------------------------------------------------- /hf_dataset_gen/audioset_strong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/hf_dataset_gen/audioset_strong.py -------------------------------------------------------------------------------- /hf_dataset_gen/metadata/audioset_eval_strong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/hf_dataset_gen/metadata/audioset_eval_strong.csv -------------------------------------------------------------------------------- /hf_dataset_gen/metadata/audioset_train_strong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/hf_dataset_gen/metadata/audioset_train_strong.csv -------------------------------------------------------------------------------- /hf_dataset_gen/metadata/class_labels_indices.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/hf_dataset_gen/metadata/class_labels_indices.csv -------------------------------------------------------------------------------- /hf_dataset_gen/metadata/class_labels_indices_strong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/hf_dataset_gen/metadata/class_labels_indices_strong.csv -------------------------------------------------------------------------------- /images/downstream_task_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/images/downstream_task_results.png -------------------------------------------------------------------------------- /inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/inference.py -------------------------------------------------------------------------------- /models/asit/ASIT_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/asit/ASIT_wrapper.py -------------------------------------------------------------------------------- /models/asit/data_transformations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/asit/data_transformations.py -------------------------------------------------------------------------------- /models/asit/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/asit/utils.py -------------------------------------------------------------------------------- /models/asit/vision_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/asit/vision_transformer.py -------------------------------------------------------------------------------- /models/atstframe/ATSTF_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/atstframe/ATSTF_wrapper.py -------------------------------------------------------------------------------- /models/atstframe/audio_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/atstframe/audio_transformer.py -------------------------------------------------------------------------------- /models/atstframe/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/atstframe/transformer.py -------------------------------------------------------------------------------- /models/beats/BEATs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/beats/BEATs.py -------------------------------------------------------------------------------- /models/beats/BEATs_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/beats/BEATs_wrapper.py -------------------------------------------------------------------------------- /models/beats/Tokenizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/beats/Tokenizers.py -------------------------------------------------------------------------------- /models/beats/backbone.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/beats/backbone.py -------------------------------------------------------------------------------- /models/beats/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/beats/modules.py -------------------------------------------------------------------------------- /models/beats/quantizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/beats/quantizer.py -------------------------------------------------------------------------------- /models/frame_mn/Frame_MN_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_mn/Frame_MN_wrapper.py -------------------------------------------------------------------------------- /models/frame_mn/block_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_mn/block_types.py -------------------------------------------------------------------------------- /models/frame_mn/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_mn/model.py -------------------------------------------------------------------------------- /models/frame_mn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_mn/utils.py -------------------------------------------------------------------------------- /models/frame_passt/fpasst.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_passt/fpasst.py -------------------------------------------------------------------------------- /models/frame_passt/fpasst_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_passt/fpasst_wrapper.py -------------------------------------------------------------------------------- /models/frame_passt/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_passt/preprocess.py -------------------------------------------------------------------------------- /models/frame_passt/vit_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/frame_passt/vit_helpers.py -------------------------------------------------------------------------------- /models/m2d/M2D_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/m2d/M2D_wrapper.py -------------------------------------------------------------------------------- /models/m2d/portable_m2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/m2d/portable_m2d.py -------------------------------------------------------------------------------- /models/prediction_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/prediction_wrapper.py -------------------------------------------------------------------------------- /models/seq_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/seq_models.py -------------------------------------------------------------------------------- /models/transformer_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/models/transformer_wrapper.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/requirements.txt -------------------------------------------------------------------------------- /resources/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/resources/README.md -------------------------------------------------------------------------------- /resources/eval_durations.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/resources/eval_durations.csv -------------------------------------------------------------------------------- /test_files/752547__iscence__milan_metro_coming_in_station.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/test_files/752547__iscence__milan_metro_coming_in_station.wav -------------------------------------------------------------------------------- /test_files/freesound_attributions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fschmid56/PretrainedSED/HEAD/test_files/freesound_attributions.txt --------------------------------------------------------------------------------