{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":52324,"databundleVersionId":6229904,"sourceType":"competition"},{"sourceId":73047,"databundleVersionId":8464136,"sourceType":"competition"}],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install opensmile\nimport opensmile\nimport pandas as pd\nimport numpy as np\nimport glob\nimport os\nimport pickle\nimport random\nimport librosa\nfrom sklearn.preprocessing import MinMaxScaler, StandardScaler\nfrom sklearn.manifold import TSNE\nimport matplotlib.pyplot as plt\nsmile = opensmile.Smile(\n    feature_set=opensmile.FeatureSet.eGeMAPSv02,\n    feature_level=opensmile.FeatureLevel.Functionals,\n    num_workers=24,\n)\nscaler = StandardScaler()","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"barishal_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_barishal*.wav')\ndf_barishal_data = smile.process_files(barishal_data)\n\nchittagong_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_chittagong*.wav')\ndf_chittagong_data = smile.process_files(chittagong_data)\n\nhabiganj_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_habiganj*.wav')\ndf_habiganj_data = smile.process_files(habiganj_data)\n\nkishoreganj_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_kishoreganj*.wav')\ndf_kishoreganj_data = smile.process_files(kishoreganj_data)\n\nnarail_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_narail*.wav')\ndf_narail_data = smile.process_files(narail_data)\n\nnarsingdi_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_narsingdi*.wav')\ndf_narsingdi_data = smile.process_files(narsingdi_data)\n\nrangpur_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_rangpur*.wav')\ndf_rangpur_data = smile.process_files(rangpur_data)\n\nsandwip_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_sandwip*.wav')\ndf_sandwip_data = smile.process_files(sandwip_data)\n\nsylhet_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_sylhet*.wav')\ndf_sylhet_data = smile.process_files(sylhet_data)\n\ntangail_data = glob.glob('/kaggle/input/ben10/ben10/16kHz_train_audio/train_tangail*.wav')\ndf_tangail_data = smile.process_files(tangail_data)\n\nmacro_data = glob.glob('/kaggle/input/bengaliai-speech-wav-dataset-0/*/*.wav')[:10000]\ndf_macro = smile.process_files(macro_data)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_barishal_data.to_csv('barishal_smile.csv')\ndf_chittagong_data.to_csv('chittagong_smile.csv')\ndf_habiganj_data.to_csv('habiganj_smile.csv')\ndf_kishoreganj_data.to_csv('kishoreganj_smile.csv')\ndf_narail_data.to_csv('narail_smile.csv')\ndf_narsingdi_data.to_csv('narsingdi_smile.csv')\ndf_rangpur_data.to_csv('rangpur_smile.csv')\ndf_sandwip_data.to_csv('sandwip_smile.csv')\ndf_sylhet_data.to_csv('sylhet_smile.csv')\ndf_tangail_data.to_csv('tangail_smile.csv')\ndf_macro.to_csv('macro_smile.csv')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}