├── .gitignore ├── README.md ├── config ├── __init__.py ├── config.py ├── daic_woz_feature_config.json ├── iemocap_feature_config.json ├── meld_feature_config.json ├── model_config.json ├── pitt_feature_config.json ├── train_SpeechFormer.json └── train_Transformer.json ├── extract_feature ├── extract_logmel.py ├── extract_spec.py └── extract_wav2vec.py ├── figures ├── README.md ├── Speech-MSA.png └── framework.png ├── metadata ├── README.md ├── metadata_daicwoz_crop_resample.csv ├── metadata_iemocap.csv ├── metadata_meld.csv └── metadata_pitt_crop.csv ├── model ├── speechformer.py └── transformer.py ├── module ├── speechformer_layer.py ├── transformer_layer.py └── utils.py ├── requirements.txt ├── train_model.py └── utils ├── __init__.py ├── avgmeter.py ├── dataset.py ├── distributed.py ├── environment.py ├── logger.py ├── model.py ├── recoder.py ├── speech_kit.py ├── toolbox.py └── write_result.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/README.md -------------------------------------------------------------------------------- /config/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/__init__.py -------------------------------------------------------------------------------- /config/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/config.py -------------------------------------------------------------------------------- /config/daic_woz_feature_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/daic_woz_feature_config.json -------------------------------------------------------------------------------- /config/iemocap_feature_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/iemocap_feature_config.json -------------------------------------------------------------------------------- /config/meld_feature_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/meld_feature_config.json -------------------------------------------------------------------------------- /config/model_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/model_config.json -------------------------------------------------------------------------------- /config/pitt_feature_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/pitt_feature_config.json -------------------------------------------------------------------------------- /config/train_SpeechFormer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/train_SpeechFormer.json -------------------------------------------------------------------------------- /config/train_Transformer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/config/train_Transformer.json -------------------------------------------------------------------------------- /extract_feature/extract_logmel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/extract_feature/extract_logmel.py -------------------------------------------------------------------------------- /extract_feature/extract_spec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/extract_feature/extract_spec.py -------------------------------------------------------------------------------- /extract_feature/extract_wav2vec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/extract_feature/extract_wav2vec.py -------------------------------------------------------------------------------- /figures/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /figures/Speech-MSA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/figures/Speech-MSA.png -------------------------------------------------------------------------------- /figures/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/figures/framework.png -------------------------------------------------------------------------------- /metadata/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/metadata/README.md -------------------------------------------------------------------------------- /metadata/metadata_daicwoz_crop_resample.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/metadata/metadata_daicwoz_crop_resample.csv -------------------------------------------------------------------------------- /metadata/metadata_iemocap.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/metadata/metadata_iemocap.csv -------------------------------------------------------------------------------- /metadata/metadata_meld.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/metadata/metadata_meld.csv -------------------------------------------------------------------------------- /metadata/metadata_pitt_crop.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/metadata/metadata_pitt_crop.csv -------------------------------------------------------------------------------- /model/speechformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/model/speechformer.py -------------------------------------------------------------------------------- /model/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/model/transformer.py -------------------------------------------------------------------------------- /module/speechformer_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/module/speechformer_layer.py -------------------------------------------------------------------------------- /module/transformer_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/module/transformer_layer.py -------------------------------------------------------------------------------- /module/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/module/utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/requirements.txt -------------------------------------------------------------------------------- /train_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/train_model.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/__init__.py -------------------------------------------------------------------------------- /utils/avgmeter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/avgmeter.py -------------------------------------------------------------------------------- /utils/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/dataset.py -------------------------------------------------------------------------------- /utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/distributed.py -------------------------------------------------------------------------------- /utils/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/environment.py -------------------------------------------------------------------------------- /utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/logger.py -------------------------------------------------------------------------------- /utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/model.py -------------------------------------------------------------------------------- /utils/recoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/recoder.py -------------------------------------------------------------------------------- /utils/speech_kit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/speech_kit.py -------------------------------------------------------------------------------- /utils/toolbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/toolbox.py -------------------------------------------------------------------------------- /utils/write_result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HappyColor/SpeechFormer/HEAD/utils/write_result.py --------------------------------------------------------------------------------