├── .gitignore ├── LICENSE ├── README.md ├── evaluation ├── OSD-VAD_evaluation_pyannote.ipynb ├── SCD_evaluation_pyannote.ipynb └── w2v2_plot_outputs_vs_refs_multitask.m ├── examples └── multitask_OSD_VAD_SCD │ ├── EN2002b.Mix-Headset_t520-540.wav │ ├── example_AMI_predictions.txt │ └── example_AMI_references.txt ├── prepare_training_data ├── OSD_VAD_generate_refs_for_wav2vec.m ├── README.md ├── SCD_generate_refs_for_wav2vec.m ├── audio_normalise_filename.m ├── get_overlap_times_from_RTTM.m ├── get_speaker_changes_from_RTTM.m ├── get_vad_times_from_RTTM.m ├── prepare_data_for_wav2vec.m ├── split_audio_for_wav2vec.m └── w2w2_combine_refs_for_multitask.m └── wav2vec2_audioFrameClassification ├── run.sh ├── run_multitask.sh ├── wav2vec2_audioFrameClassification.py └── wav2vec2_audioFrameClassification_multitask.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/README.md -------------------------------------------------------------------------------- /evaluation/OSD-VAD_evaluation_pyannote.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/evaluation/OSD-VAD_evaluation_pyannote.ipynb -------------------------------------------------------------------------------- /evaluation/SCD_evaluation_pyannote.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/evaluation/SCD_evaluation_pyannote.ipynb -------------------------------------------------------------------------------- /evaluation/w2v2_plot_outputs_vs_refs_multitask.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/evaluation/w2v2_plot_outputs_vs_refs_multitask.m -------------------------------------------------------------------------------- /examples/multitask_OSD_VAD_SCD/EN2002b.Mix-Headset_t520-540.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/examples/multitask_OSD_VAD_SCD/EN2002b.Mix-Headset_t520-540.wav -------------------------------------------------------------------------------- /examples/multitask_OSD_VAD_SCD/example_AMI_predictions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/examples/multitask_OSD_VAD_SCD/example_AMI_predictions.txt -------------------------------------------------------------------------------- /examples/multitask_OSD_VAD_SCD/example_AMI_references.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/examples/multitask_OSD_VAD_SCD/example_AMI_references.txt -------------------------------------------------------------------------------- /prepare_training_data/OSD_VAD_generate_refs_for_wav2vec.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/OSD_VAD_generate_refs_for_wav2vec.m -------------------------------------------------------------------------------- /prepare_training_data/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/README.md -------------------------------------------------------------------------------- /prepare_training_data/SCD_generate_refs_for_wav2vec.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/SCD_generate_refs_for_wav2vec.m -------------------------------------------------------------------------------- /prepare_training_data/audio_normalise_filename.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/audio_normalise_filename.m -------------------------------------------------------------------------------- /prepare_training_data/get_overlap_times_from_RTTM.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/get_overlap_times_from_RTTM.m -------------------------------------------------------------------------------- /prepare_training_data/get_speaker_changes_from_RTTM.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/get_speaker_changes_from_RTTM.m -------------------------------------------------------------------------------- /prepare_training_data/get_vad_times_from_RTTM.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/get_vad_times_from_RTTM.m -------------------------------------------------------------------------------- /prepare_training_data/prepare_data_for_wav2vec.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/prepare_data_for_wav2vec.m -------------------------------------------------------------------------------- /prepare_training_data/split_audio_for_wav2vec.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/split_audio_for_wav2vec.m -------------------------------------------------------------------------------- /prepare_training_data/w2w2_combine_refs_for_multitask.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/prepare_training_data/w2w2_combine_refs_for_multitask.m -------------------------------------------------------------------------------- /wav2vec2_audioFrameClassification/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/wav2vec2_audioFrameClassification/run.sh -------------------------------------------------------------------------------- /wav2vec2_audioFrameClassification/run_multitask.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/wav2vec2_audioFrameClassification/run_multitask.sh -------------------------------------------------------------------------------- /wav2vec2_audioFrameClassification/wav2vec2_audioFrameClassification.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/wav2vec2_audioFrameClassification/wav2vec2_audioFrameClassification.py -------------------------------------------------------------------------------- /wav2vec2_audioFrameClassification/wav2vec2_audioFrameClassification_multitask.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mkunes/w2v2_audioFrameClassification/HEAD/wav2vec2_audioFrameClassification/wav2vec2_audioFrameClassification_multitask.py --------------------------------------------------------------------------------