{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "Z7js94bngg30" }, "source": [ "# Data preprocessing" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "L2OENoC1PLWf" }, "outputs": [], "source": [ "import os\n", "from tqdm.auto import tqdm\n", "tqdm.pandas()" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2022-06-02 09:58:11-- https://files.deeppavlov.ai/field-matters/releases/demo/sound.zip\n", "Resolving files.deeppavlov.ai (files.deeppavlov.ai)... 178.63.27.41\n", "Connecting to files.deeppavlov.ai (files.deeppavlov.ai)|178.63.27.41|:443... connected.\n", "HTTP request sent, awaiting response... 416 Requested Range Not Satisfiable\n", "\n", " The file is already fully retrieved; nothing to do.\n", "\n", "--2022-06-02 09:58:12-- https://files.deeppavlov.ai/field-matters/releases/demo/dia_data.csv\n", "Resolving files.deeppavlov.ai (files.deeppavlov.ai)... 178.63.27.41\n", "Connecting to files.deeppavlov.ai (files.deeppavlov.ai)|178.63.27.41|:443... connected.\n", "HTTP request sent, awaiting response... 416 Requested Range Not Satisfiable\n", "\n", " The file is already fully retrieved; nothing to do.\n", "\n", "Archive: sound.zip\n", " inflating: audio_to_release/ckt/A chatterbox and a wanton girl-0-0.mp4 \n", " inflating: audio_to_release/ckt/A chatterbox and a wanton girl-1-0.mp4 \n", " inflating: audio_to_release/ckt/An evil spirit and a dicky bird-1-0.mp4 \n", " inflating: audio_to_release/ckt/An evil spirit and a dicky bird-2-0.mp4 \n", " inflating: audio_to_release/ckt/An evil spirit and a dicky bird-2-1.mp4 \n", " inflating: audio_to_release/ckt/Being a child-0-0.mp4 \n", " inflating: audio_to_release/ckt/Being a child-0-1.mp4 \n", " inflating: audio_to_release/ckt/Being a child-0-3.mp4 \n", " inflating: audio_to_release/ckt/Being a child-1-0.mp4 \n", " inflating: audio_to_release/ckt/Being a child-1-6.mp4 \n", " inflating: audio_to_release/ckt/Boots-2-0.mp4 \n", " inflating: audio_to_release/ckt/Brandy-0-3.mp4 \n", " inflating: audio_to_release/ckt/Endless fairy tale-0-0.mp4 \n", " inflating: audio_to_release/ckt/Endless fairy tale-1-0.mp4 \n", " inflating: audio_to_release/ckt/Eraqor-0-1.mp4 \n", " inflating: audio_to_release/ckt/Eraqor-1-1.mp4 \n", " inflating: audio_to_release/ckt/Faces-1-0.mp4 \n", " inflating: audio_to_release/ckt/Fishing with Ilya-1-0.mp4 \n", " inflating: audio_to_release/ckt/Fishing with Ilya-1-3.mp4 \n", " inflating: audio_to_release/ckt/Fishing with Ilya-2-0.mp4 \n", " inflating: audio_to_release/ckt/Fishing with Ilya-2-1.mp4 \n", " inflating: audio_to_release/ckt/Fly agarics-1-0.mp4 \n", " inflating: audio_to_release/ckt/Fly agarics-1-1.mp4 \n", " inflating: audio_to_release/ckt/Fly agarics-2-0.mp4 \n", " inflating: audio_to_release/ckt/Gathering mushrooms-0-0.mp4 \n", " inflating: audio_to_release/ckt/GUM-0-3.mp4 \n", " inflating: audio_to_release/ckt/GUM-1-4.mp4 \n", " inflating: audio_to_release/ckt/Guy-0-0.mp4 \n", " inflating: audio_to_release/ckt/Having bear ears-0-2.mp4 \n", " inflating: audio_to_release/ckt/Hooligan-0-0.mp4 \n", " inflating: audio_to_release/ckt/I am from Chukotka-0-1.mp4 \n", " inflating: audio_to_release/ckt/I am from Chukotka-1-2.mp4 \n", " inflating: audio_to_release/ckt/Ice Age-0-3.mp4 \n", " inflating: audio_to_release/ckt/Ice Age-1-2.mp4 \n", " inflating: audio_to_release/ckt/Incident-0-0.mp4 \n", " inflating: audio_to_release/ckt/Incident-2-0.mp4 \n", " inflating: audio_to_release/ckt/Kettle-1-0.mp4 \n", " inflating: audio_to_release/ckt/Kettle-1-4.mp4 \n", " inflating: audio_to_release/ckt/Kettle-2-0.mp4 \n", " inflating: audio_to_release/ckt/Kettle-2-3.mp4 \n", " inflating: audio_to_release/ckt/Kettle-2-5.mp4 \n", " inflating: audio_to_release/ckt/Knives-0-2.mp4 \n", " inflating: audio_to_release/ckt/Knives-1-0.mp4 \n", " inflating: audio_to_release/ckt/Knives-2-0.mp4 \n", " inflating: audio_to_release/ckt/Knives-2-1.mp4 \n", " inflating: audio_to_release/ckt/Larvae-0-2.mp4 \n", " inflating: audio_to_release/ckt/Larvae-1-1.mp4 \n", " inflating: audio_to_release/ckt/Larvae-2-0.mp4 \n", " inflating: audio_to_release/ckt/Larvae-2-1.mp4 \n", "audio_to_release/ckt/Let’s go wash to Egvekinot-0-3.mp4: mismatching \"local\" filename (audio_to_release/ckt/LetтАЩs go wash to Egvekinot-0-3.mp4),\n", " continuing with \"central\" filename version\n", " inflating: audio_to_release/ckt/Let’s go wash to Egvekinot-0-3.mp4 \n", "audio_to_release/ckt/Let’s go wash to Egvekinot-1-1.mp4: mismatching \"local\" filename (audio_to_release/ckt/LetтАЩs go wash to Egvekinot-1-1.mp4),\n", " continuing with \"central\" filename version\n", " inflating: audio_to_release/ckt/Let’s go wash to Egvekinot-1-1.mp4 \n", "audio_to_release/ckt/Let’s go wash to Egvekinot-1-2.mp4: mismatching \"local\" filename (audio_to_release/ckt/LetтАЩs go wash to Egvekinot-1-2.mp4),\n", " continuing with \"central\" filename version\n", " inflating: audio_to_release/ckt/Let’s go wash to Egvekinot-1-2.mp4 \n", "audio_to_release/ckt/Let’s go wash to Egvekinot-2-1.mp4: mismatching \"local\" filename (audio_to_release/ckt/LetтАЩs go wash to Egvekinot-2-1.mp4),\n", " continuing with \"central\" filename version\n", " inflating: audio_to_release/ckt/Let’s go wash to Egvekinot-2-1.mp4 \n", " inflating: audio_to_release/ckt/Life-0-0.mp4 \n", " inflating: audio_to_release/ckt/Life-0-1.mp4 \n", " inflating: audio_to_release/ckt/Mother-0-1.mp4 \n", " inflating: audio_to_release/ckt/Mother-0-2.mp4 \n", " inflating: audio_to_release/ckt/Mother-0-3.mp4 \n", " inflating: audio_to_release/ckt/Mother-1-3.mp4 \n", " inflating: audio_to_release/ckt/Mushrooming with Pauline-0-0.mp4 \n", " inflating: audio_to_release/ckt/Mushrooming with Pauline-1-1.mp4 \n", " inflating: audio_to_release/ckt/Mushrooms-1-0.mp4 \n", " inflating: audio_to_release/ckt/Not eating larvae-0-1.mp4 \n", " inflating: audio_to_release/ckt/Not eating larvae-0-4.mp4 \n", " inflating: audio_to_release/ckt/Not eating larvae-0-6.mp4 \n", " inflating: audio_to_release/ckt/Not eating larvae-0-8.mp4 \n", " inflating: audio_to_release/ckt/Not eating larvae-1-7.mp4 \n", " inflating: audio_to_release/ckt/Not eating larvae-2-3.mp4 \n", " inflating: audio_to_release/ckt/On a daily basis-0-4.mp4 \n", " inflating: audio_to_release/ckt/On a daily basis-1-1.mp4 \n", " inflating: audio_to_release/ckt/Parents-0-0.mp4 \n", " inflating: audio_to_release/ckt/Parents-1-1.mp4 \n", " inflating: audio_to_release/ckt/Raven and fox-1-2.mp4 \n", " inflating: audio_to_release/ckt/Raven and fox-2-1.mp4 \n", " inflating: audio_to_release/ckt/Running Pauline-0-0.mp4 \n", " inflating: audio_to_release/ckt/Shaman-2-1.mp4 \n", " inflating: audio_to_release/ckt/Telyopka-0-2.mp4 \n", " inflating: audio_to_release/ckt/Telyopka-1-1.mp4 \n", " inflating: audio_to_release/ckt/Telyopka-2-0.mp4 \n", " inflating: audio_to_release/ckt/Telyopka-2-2.mp4 \n", " inflating: audio_to_release/ckt/Tent-0-0.mp4 \n", " inflating: audio_to_release/ckt/Tenylqot and Eqelqot-0-0.mp4 \n", " inflating: audio_to_release/ckt/The day before yesterday-0-0.mp4 \n", " inflating: audio_to_release/ckt/The race to death-0-0.mp4 \n", " inflating: audio_to_release/ckt/Transhumance-0-0.mp4 \n", " inflating: audio_to_release/ckt/Transhumance-0-6.mp4 \n", " inflating: audio_to_release/ckt/Transhumance-1-2.mp4 \n", " inflating: audio_to_release/ckt/Transhumance-1-3.mp4 \n", " inflating: audio_to_release/ckt/Transhumance-2-1.mp4 \n", " inflating: audio_to_release/ckt/Vacation-0-1.mp4 \n", " inflating: audio_to_release/ckt/Vacation-0-2.mp4 \n", " inflating: audio_to_release/ckt/Vacation-1-1.mp4 \n", " inflating: audio_to_release/ckt/Walk-0-1.mp4 \n", " inflating: audio_to_release/ckt/Walk-2-1.mp4 \n", " inflating: audio_to_release/ckt/Water cart-2-2.mp4 \n", " inflating: audio_to_release/ckt/Water cart-2-4.mp4 \n", " inflating: audio_to_release/ckt/WC-0-0.mp4 \n", " inflating: audio_to_release/ckt/Worms-0-0.mp4 \n", " inflating: audio_to_release/ckt/Wyttal-1-1.mp4 \n", " inflating: audio_to_release/ckt/Wyttal-2-1.mp4 \n", " inflating: audio_to_release/evn/1998_Sovrechka_Saygotina_Vera_LR-0-1.mp4 \n", " inflating: audio_to_release/evn/1998_Sovrechka_Saygotina_Vera_LR-0-5.mp4 \n", " inflating: audio_to_release/evn/1998_Sovrechka_Saygotina_Vera_LR-1-0.mp4 \n", " inflating: audio_to_release/evn/1998_Sovrechka_Saygotina_Vera_LR-2-0.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LO-0-0.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LO-0-3.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LO-2-3.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LO-2-4.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR1-0-0.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR1-0-5.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR1-2-1.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR1-2-3.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR2-0-1.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR2-2-0.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR2-2-1.mp4 \n", " inflating: audio_to_release/evn/2005_Poligus_Khadonchina_LR2-2-2.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Bolshoe_Sovetskoe_Saygotin_LO2-0-2.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Bolshoe_Sovetskoe_Saygotin_LO2-1-1.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Bolshoe_Sovetskoe_Saygotin_LO2-2-1.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Bolshoe_Sovetskoe_Saygotin_LO3-1-1.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Bolshoe_Sovetskoe_Saygotin_LR-0-3.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Podvalnoe_Buneeva_LR-0-1.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Podvalnoe_Buneeva_LR-0-2.mp4 \n", " inflating: audio_to_release/evn/2006_Ozero_Podvalnoe_Buneeva_LR-1-1.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-0-5.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-0-6.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-0-7.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-1-2.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-1-3.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-1-6.mp4 \n", " inflating: audio_to_release/evn/2007 Ekonda Pankagir L-Av-2-4.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM1-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM10-0-4.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM10-1-4.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM10-1-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM10-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM2-0-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM2-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM2-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM3-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM4-0-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM4-0-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM4-0-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM4-0-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM4-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM4-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM7-0-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM7-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM7-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM7-1-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM8-0-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM9-0-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM9-0-4.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM9-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FM9-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk10-0-6.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk10-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk10-1-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk10-1-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk10-2-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk10-2-4.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk2-0-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk2-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk2-1-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk3-2-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk5-0-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk6-1-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk6-2-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk6-2-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-0-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-0-6.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-1-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-1-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-2-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk7-2-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-0-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-0-8.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-1-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-1-9.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-2-10.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-2-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-2-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk8-2-9.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-0-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-0-6.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-2-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-2-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_FSk9-2-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-0-12.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-0-16.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-0-2.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-0-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-0-9.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-1-10.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-1-14.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-1-3.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-1-8.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-1-9.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-2-17.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-2-6.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR1-2-9.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-1-4.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-1-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-1-7.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-1-8.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-2-5.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Eldogir_Valentina_LR2-2-8.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Khukochar_LRFragm-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Khukochar_LRFragm-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Chirinda_Khutokogir_Dmitriy_LF_L-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Khutokogir_Grigoriy_LAv-0-2.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Khutokogir_Grigoriy_LAv-0-5.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Khutokogir_Grigoriy_LAv-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Khutokogir_Grigoriy_LAv-1-2.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Khutokogir_Grigoriy_LAv-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Kombagir_Anton_LAv-0-2.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Kombagir_Anton_LAv-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Kombagir_Anton_LAv-2-3.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Udygir_Viktor_FSham-0-0.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Udygir_Viktor_FSham-1-4.mp4 \n", " inflating: audio_to_release/evn/2007_Ekonda_Udygir_Viktor_FSham-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Dmitriev_LO1-0-1.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Dmitriev_LO1-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Dmitriev_LO2-1-2.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Yastrikova_FSk2-1-4.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Yastrikova_FSk2-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Yastrikova_FSk5-0-2.mp4 \n", " inflating: audio_to_release/evn/2007_Mutoray_Yastrikova_FSk5-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR1-0-2.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR1-2-0.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR1-2-1.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR1-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR3-0-6.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR3-1-3.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR3-1-5.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR3-1-8.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR3-2-3.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR3-2-6.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR4-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR6_1-0-6.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR6_1-1-1.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreeva_LR6_1-2-2.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR1-0-5.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR1-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR1-2-1.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR1-2-3.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR1-2-5.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-0-10.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-0-11.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-0-13.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-0-14.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-0-7.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-1-0.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-1-10.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-1-12.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-1-4.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-2-10.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-2-4.mp4 \n", " inflating: audio_to_release/evn/2007_Strelka_Andreev_LR3-2-7.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Sidorov_Konstantin_LAvPart1-0-4.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Sidorov_Konstantin_LAvPart1-0-7.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Sidorov_Konstantin_LAvPart1-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_FM-0-2.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_FM-1-1.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_FM-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_FM-2-1.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LAv_MPEG1_WAV-0-2.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR1_MP4-0-3.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR1_MP4-0-4.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR1_MP4-1-1.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR1_MP4-2-2.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR2-0-2.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR2-0-3.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR2-1-0.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR2-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Kislokan_Udygir_Valentina_LR2-2-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Eldygir_Liliya_LAv-1-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Eldygir_Liliya_LAv-1-5.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Eldygir_Liliya_LAv-2-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Eldygir_Liliya_LAv-2-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Eldygir_Liliya_LR1-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_FB_2-1-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_FB_2-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_FB_2-2-1.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR1_2-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR1_2-0-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR1_2-1-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR1_3-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR1_3-1-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR3-0-4.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR3-0-6.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR3-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR3-2-10.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR3-2-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tura_Lapuko_LR3-2-5.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Bondareva_LR1-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Bondareva_LR1-2-1.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Danil_LRFSk_2-1-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Danil_LRFSk_2-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Danil_LR_WAV-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Danil_LR_WAV-2-1.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Danil_LR_WAV-2-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-0-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-0-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-1-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-2-1.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-2-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Khukochar_Maksim_LR-2-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Lapushkina_LA2-1-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Lapushkina_LA2-2-1.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Pankagir_FSk-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Pankagir_FSk-1-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Pankagir_FSk-2-2.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv1-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv1-1-1.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv1-1-4.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv1-1-5.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv1-2-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-0-0.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-0-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-1-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-1-8.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-2-4.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-2-6.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv2-2-7.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-0-12.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-0-13.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-0-3.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-0-9.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-1-12.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-1-6.mp4 \n", " inflating: audio_to_release/evn/2008_Tutonchany_Uvachan_Inna_LAv3-2-1.mp4 \n", " inflating: audio_to_release/evn/2009 Sym Boyarin Georgiy L-R 4-1-0.mp4 \n", " inflating: audio_to_release/evn/2009 Sym Boyarin Georgiy L-R 4-1-3.mp4 \n", " inflating: audio_to_release/evn/2009_Sym_Boyarin_Georgiy_LR3-0-0.mp4 \n", " inflating: audio_to_release/evn/2009_Sym_Boyarin_Georgiy_LR3-0-3.mp4 \n", " inflating: audio_to_release/evn/2009_Sym_Boyarin_Georgiy_LR3-1-0.mp4 \n", " inflating: audio_to_release/evn/2009_Sym_Boyarin_Georgiy_LR3-1-1.mp4 \n", " inflating: audio_to_release/evn/2009_Sym_Boyarin_Georgiy_LR3-1-2.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-0-0.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-0-21.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-0-23.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-0-6.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-11.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-13.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-21.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-3.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-4.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-7.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-8.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-1-9.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-2-3.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-2-6.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR1-2-8.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR2-0-3.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR2-1-1.mp4 \n", " inflating: audio_to_release/evn/2010_Bely_Yar_Ivigin_Vladimir_LR2-1-3.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Chemprogir_Antonina_Dmitriyevna_LB-0-3.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Chemprogir_Antonina_Dmitriyevna_LB-0-4.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Chemprogir_Antonina_Dmitriyevna_LB-1-3.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Chemprogir_Antonina_Dmitriyevna_LB-2-2.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_TurskayaMinnaDmitriyevna_FB1-1-0.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Turskaya_Minna_Dmitriyevna_FB2-0-0.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Turskaya_Minna_Dmitriyevna_FB2-0-2.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Turskaya_Minna_Dmitriyevna_FB2-2-0.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Turskaya_Minna_Dmitriyevna_L-2-1.mp4 \n", " inflating: audio_to_release/evn/2011_Hantayskoye_Ozero_Turskaya_Minna_Dmitriyevna_LR1-0-0.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_TamaraAndreevna_FM1-0-3.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_TamaraAndreevna_FM1-0-4.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_TamaraAndreevna_FM1-0-5.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-1-3.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2-0.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2-1.mp4 \n", " inflating: audio_to_release/evn/2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2-3.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-12.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-15.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-17.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-19.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-27.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-0-28.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-11.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-17.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-19.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-22.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-23.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-24.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-1-9.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-2-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-2-10.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-2-23.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_2-2-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-0-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-0-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-0-6.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-0-7.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-1-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-1-8.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-2-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-2-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-2-6.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_3-2-8.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_4-0-3.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_4-0-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_4-1-3.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_4-2-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_4-2-6.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-0-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-0-15.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-0-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-0-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-1-10.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-1-13.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-1-14.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-1-3.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-1-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-11.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-12.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-6.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-7.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ANF_ZVK-V_Ushemnure_5-2-8.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_1-0-7.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_1-1-10.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_1-1-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_1-1-8.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_1-2-7.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-0-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-0-14.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-0-25.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-0-27.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-0-35.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-0-7.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-14.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-19.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-22.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-28.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-1-7.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-12.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-16.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-19.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-30.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-32.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-33.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-100118-ZIE_ZVK-Biografiya_2-2-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-TFP_ZVK-Bliny-0-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-TFP_ZVK-Bliny-0-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-YeNP_ZVK-Tancy-0-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-YeNP_ZVK-Tancy-1-4.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-YeNP_ZVK-Tancy-2-3.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-ZVK_TFP-Tumna-tum-tum-0-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-110118-ZVK_TFP-Tumna-tum-tum-0-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-AVYe-Velikoe_protivostoyanie-0-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-AVYe-Velikoe_protivostoyanie-1-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-AVYe-Velikoe_protivostoyanie-1-5.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-AVYe-Velikoe_protivostoyanie-2-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-AVYe-Velikoe_protivostoyanie-2-6.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-EIK-na_beregax_Nemdy-0-2.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-TAT-Prividenie_v_shkole-0-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-TAT-Prividenie_v_shkole-2-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-TFP-Metallolom-2-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-TFP-Operaciya_Ogurcy-1-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-TFP-Paporotnik-1-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-VVKa-Shkola-1-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-VVKa-Staryj_Torjal-0-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-VVKa-Staryj_Torjal-2-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-YePT_VVKa-Sestra_Lena_o_zhizni-1-1.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-YePT_VVKa-Sestra_Lena_o_zhizni-2-0.mp4 \n", " inflating: audio_to_release/mhr/mhr-StTor-2000_2001-YePT_VVKa-Sestra_Lena_o_zhizni-2-1.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-15.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-19.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-2.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-21.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-23.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-25.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-27.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-4.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-0-6.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-1-0.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-1-1.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-1-15.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-1-21.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-1-25.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-1-3.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-2-1.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-2-14.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-2-17.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-2-2.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-2-20.mp4 \n", " inflating: audio_to_release/mhr/mhr_rus-StTor-100118-ANF_ZVK-V_Ushemnure_1-2-26.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-0-12.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-0-13.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-0-3.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-0-8.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-1-10.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-1-7.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-1-8.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-2-1.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-2-10.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-2-11.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-2-13.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-2-6.mp4 \n", " inflating: audio_to_release/sah/game_1-885s-2-9.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-0-1.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-0-10.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-0-12.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-0-14.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-1-11.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-1-3.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-1-5.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-1-9.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-2-10.mp4 \n", " inflating: audio_to_release/sah/game_1785-2605s-2-12.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-0-14.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-1-10.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-1-12.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-1-13.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-1-2.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-1-3.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-1-5.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-2-13.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-2-5.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-2-6.mp4 \n", " inflating: audio_to_release/sah/game_2605-3500s-2-7.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-0.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-10.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-13.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-14.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-2.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-3.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-6.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-0-9.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-2-12.mp4 \n", " inflating: audio_to_release/sah/game_3500-4400s-2-4.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-0-2.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-0-7.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-1-12.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-1-13.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-2-10.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-2-5.mp4 \n", " inflating: audio_to_release/sah/game_4400-5300s-2-9.mp4 \n", " inflating: audio_to_release/sah/game_5300-6200s-0-12.mp4 \n", " inflating: audio_to_release/sah/game_5300-6200s-1-1.mp4 \n", " inflating: audio_to_release/sah/game_5300-6200s-1-10.mp4 \n", " inflating: audio_to_release/sah/game_5300-6200s-1-13.mp4 \n", " inflating: audio_to_release/sah/game_5300-6200s-2-11.mp4 \n", " inflating: audio_to_release/sah/game_5300-6200s-2-5.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-0-13.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-0-7.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-1-1.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-1-13.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-1-4.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-1-7.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-1-8.mp4 \n", " inflating: audio_to_release/sah/game_6200-7100s-2-2.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-0-11.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-1-0.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-1-1.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-1-9.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-2-12.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-2-14.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-2-2.mp4 \n", " inflating: audio_to_release/sah/game_7100-8000s-2-6.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-0-12.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-0-4.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-1-0.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-1-10.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-1-6.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-2-3.mp4 \n", " inflating: audio_to_release/sah/game_8000-8788s-2-7.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-0-1.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-0-11.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-0-12.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-0-13.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-0-3.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-1-10.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-1-14.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-2-0.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-2-13.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-2-2.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-2-3.mp4 \n", " inflating: audio_to_release/sah/game_885-1785s-2-4.mp4 \n", " inflating: audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", " inflating: audio_to_release/yrk/Katushka_VorontsovoNENETS_A_48-16.wav \n", " inflating: audio_to_release/yrk/TOYa_audio_TNenets.wav \n" ] } ], "source": [ "!wget -c https://files.deeppavlov.ai/field-matters/releases/demo/sound.zip\n", "!wget -c https://files.deeppavlov.ai/field-matters/releases/demo/dia_data.csv\n", "!unzip sound.zip #your audios here" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "id": "4b9mIJG6eg2x" }, "outputs": [], "source": [ "import pandas as pd\n", "df = pd.read_csv('dia_data.csv') #your dataset" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "kOEgS1aPifVI" }, "outputs": [], "source": [ "df['fpath'] = './audio_to_release/' + df['lang'] + '/' + df['source']" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "id": "L0w_T09MjDIs" }, "outputs": [], "source": [ "df['fpath'] = df['fpath'].apply(lambda x: x.replace(' ', '_')) #removing spaces in dataset's paths" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "id": "NuEpf8lSOxYY" }, "outputs": [], "source": [ "all_paths = df['fpath']\n", "all_paths = list(set(all_paths))" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "id": "xJK3XutQNurQ" }, "outputs": [], "source": [ "df = df.reset_index() #adding indexes(id)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "id": "4cygiPVzEXYP" }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
fpath0coord_startcoord_end
0./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV...{'start': [19.529], 'end': [21.29600000000005]...19.52938.354
1./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV...{'start': [20.15099999999996], 'end': [21.3250...20.15139.441
2./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV...{'start': [20.423999999999968], 'end': [22.865...20.42438.767
3./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV...{'start': [22.1099999999999], 'end': [22.70299...22.11040.325
4./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV...{'start': [18.18100000000001], 'end': [21.9610...18.18141.311
...............
209./audio_to_release/sah/game_885-1785s-2-2.mp4{'start': [21.166999999999998], 'end': [21.523...21.16737.762
210./audio_to_release/sah/game_885-1785s-2-3.mp4{'start': [25.99700000000001], 'end': [29.4730...25.99741.180
211./audio_to_release/sah/game_885-1785s-2-4.mp4{'start': [21.35500000000001], 'end': [22.3290...21.35542.167
212./audio_to_release/yrk/TOYa_audio_TNenets.wav{'start': [0.2339999999999999], 'end': [5.186]...0.23439.866
213./audio_to_release/yrk/es100708_MatjPelaNEN.WAV{'start': [48.95399999999999], 'end': [49.525]...48.95449.525
\n", "

214 rows × 4 columns

\n", "
" ], "text/plain": [ " fpath \\\n", "0 ./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV... \n", "1 ./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV... \n", "2 ./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV... \n", "3 ./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV... \n", "4 ./audio_to_release/mhr/mhr-StTor-100118-ANF_ZV... \n", ".. ... \n", "209 ./audio_to_release/sah/game_885-1785s-2-2.mp4 \n", "210 ./audio_to_release/sah/game_885-1785s-2-3.mp4 \n", "211 ./audio_to_release/sah/game_885-1785s-2-4.mp4 \n", "212 ./audio_to_release/yrk/TOYa_audio_TNenets.wav \n", "213 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "\n", " 0 coord_start coord_end \n", "0 {'start': [19.529], 'end': [21.29600000000005]... 19.529 38.354 \n", "1 {'start': [20.15099999999996], 'end': [21.3250... 20.151 39.441 \n", "2 {'start': [20.423999999999968], 'end': [22.865... 20.424 38.767 \n", "3 {'start': [22.1099999999999], 'end': [22.70299... 22.110 40.325 \n", "4 {'start': [18.18100000000001], 'end': [21.9610... 18.181 41.311 \n", ".. ... ... ... \n", "209 {'start': [21.166999999999998], 'end': [21.523... 21.167 37.762 \n", "210 {'start': [25.99700000000001], 'end': [29.4730... 25.997 41.180 \n", "211 {'start': [21.35500000000001], 'end': [22.3290... 21.355 42.167 \n", "212 {'start': [0.2339999999999999], 'end': [5.186]... 0.234 39.866 \n", "213 {'start': [48.95399999999999], 'end': [49.525]... 48.954 49.525 \n", "\n", "[214 rows x 4 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df2 = pd.DataFrame(df.drop(['speaker', 'source', 'lang', 'index'], axis=1).groupby('fpath').apply(dict)).reset_index()\n", "df2['coord_start'] = df2[0].apply(lambda x: list(x['start'])[0])\n", "df2['coord_end'] = df2[0].apply(lambda x: list(x['end'])[-1])\n", "df2" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "id": "vxvE1zufM6bv" }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "8b52f899925847bc800264e1415f1053", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/214 [00:00=0.8.0 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (0.8.1)\n", "Requirement already satisfied: pandas>=0.18.0 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (0.25.3)\n", "Requirement already satisfied: Pillow>=6.2.1 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (9.0.0)\n", "Requirement already satisfied: sortedcollections>=1.0.1 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (2.1.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (4.0.1)\n", "Requirement already satisfied: pyannote.metrics>=2.3 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (3.2)\n", "Requirement already satisfied: tensorboard>=2.0.0 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (2.3.0)\n", "Requirement already satisfied: sortedcontainers>=2.0.4 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (2.4.0)\n", "Requirement already satisfied: scikit-learn>=0.20.2 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (0.21.2)\n", "Requirement already satisfied: pyannote.pipeline<2.0.0,>=1.5.2 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (1.5.2)\n", "Requirement already satisfied: pescador>=2.1.0 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (2.1.0)\n", "Requirement already satisfied: tqdm>=4.29.1 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (4.64.0)\n", "Requirement already satisfied: pyannote.database>=4.0 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.audio) (4.1.3)\n", "Requirement already satisfied: soundfile>=0.10.2 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (0.10.3.post1)\n", "Requirement already satisfied: cachetools>=2.0.0 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (4.2.4)\n", "Requirement already satisfied: pyYAML>=3.12 in /home/user/conda/lib/python3.7/site-packages (from pyannote.audio) (6.0)\n", "Requirement already satisfied: simplejson>=3.8.1 in /home/user/conda/lib/python3.7/site-packages (from pyannote.core) (3.17.6)\n", "Requirement already satisfied: scipy>=1.1 in /home/user/conda/lib/python3.7/site-packages (from pyannote.core) (1.4.1)\n", "Requirement already satisfied: numpy>=1.10.4 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.core) (1.18.0)\n", "Requirement already satisfied: audioread>=2.0.0 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (2.1.9)\n", "Requirement already satisfied: pooch>=1.0 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (1.5.2)\n", "Requirement already satisfied: decorator>=3.0.0 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (5.1.1)\n", "Requirement already satisfied: numba>=0.43.0 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (0.55.0)\n", "Requirement already satisfied: resampy>=0.2.2 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (0.2.2)\n", "Requirement already satisfied: packaging>=20.0 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (21.3)\n", "Requirement already satisfied: joblib>=0.14 in /home/user/conda/lib/python3.7/site-packages (from librosa>=0.8.0->pyannote.audio) (1.1.0)\n", "Requirement already satisfied: pytz>=2017.2 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pandas>=0.18.0->pyannote.audio) (2019.1)\n", "Requirement already satisfied: python-dateutil>=2.6.1 in /home/user/conda/lib/python3.7/site-packages (from pandas>=0.18.0->pyannote.audio) (2.8.2)\n", "Requirement already satisfied: six>=1.8 in /home/user/conda/lib/python3.7/site-packages (from pescador>=2.1.0->pyannote.audio) (1.16.0)\n", "Requirement already satisfied: pyzmq>=15.0 in /home/user/conda/lib/python3.7/site-packages (from pescador>=2.1.0->pyannote.audio) (22.3.0)\n", "Requirement already satisfied: typer[all]>=0.2.1 in /home/user/conda/lib/python3.7/site-packages (from pyannote.database>=4.0->pyannote.audio) (0.4.0)\n", "Requirement already satisfied: tabulate>=0.7.7 in /home/user/conda/lib/python3.7/site-packages (from pyannote.metrics>=2.3->pyannote.audio) (0.8.9)\n", "Requirement already satisfied: matplotlib>=2.0.0 in /home/user/conda/lib/python3.7/site-packages (from pyannote.metrics>=2.3->pyannote.audio) (3.5.1)\n", "Requirement already satisfied: sympy>=1.1 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.metrics>=2.3->pyannote.audio) (1.10.1)\n", "Requirement already satisfied: docopt>=0.6.2 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.metrics>=2.3->pyannote.audio) (0.6.2)\n", "Requirement already satisfied: optuna>=1.4 in /home/user/conda/lib/python3.7/site-packages (from pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (2.10.0)\n", "Requirement already satisfied: filelock>=3.0.10 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (3.7.0)\n", "Requirement already satisfied: cffi>=1.0 in /home/user/conda/lib/python3.7/site-packages (from soundfile>=0.10.2->pyannote.audio) (1.15.0)\n", "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (0.4.6)\n", "Requirement already satisfied: werkzeug>=0.11.15 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (2.0.2)\n", "Requirement already satisfied: google-auth<2,>=1.6.3 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (1.35.0)\n", "Requirement already satisfied: markdown>=2.6.8 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (3.3.6)\n", "Requirement already satisfied: requests<3,>=2.21.0 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (2.22.0)\n", "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (1.8.1)\n", "Requirement already satisfied: wheel>=0.26 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (0.37.1)\n", "Requirement already satisfied: protobuf>=3.6.0 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (3.19.3)\n", "Requirement already satisfied: absl-py>=0.4 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (1.0.0)\n", "Requirement already satisfied: grpcio>=1.24.3 in /home/user/conda/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (1.43.0)\n", "Requirement already satisfied: setuptools>=41.0.0 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from tensorboard>=2.0.0->pyannote.audio) (60.5.0)\n", "Requirement already satisfied: pycparser in /home/user/conda/lib/python3.7/site-packages (from cffi>=1.0->soundfile>=0.10.2->pyannote.audio) (2.21)\n", "Requirement already satisfied: pyasn1-modules>=0.2.1 in /home/user/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=2.0.0->pyannote.audio) (0.2.8)\n", "Requirement already satisfied: rsa<5,>=3.1.4 in /home/user/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=2.0.0->pyannote.audio) (4.8)\n", "Requirement already satisfied: requests-oauthlib>=0.7.0 in /home/user/conda/lib/python3.7/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=2.0.0->pyannote.audio) (1.3.0)\n", "Requirement already satisfied: importlib-metadata>=4.4 in /home/user/conda/lib/python3.7/site-packages (from markdown>=2.6.8->tensorboard>=2.0.0->pyannote.audio) (4.10.1)\n", "Requirement already satisfied: pyparsing>=2.2.1 in /home/user/conda/lib/python3.7/site-packages (from matplotlib>=2.0.0->pyannote.metrics>=2.3->pyannote.audio) (3.0.7)\n", "Requirement already satisfied: kiwisolver>=1.0.1 in /home/user/conda/lib/python3.7/site-packages (from matplotlib>=2.0.0->pyannote.metrics>=2.3->pyannote.audio) (1.3.2)\n", "Requirement already satisfied: cycler>=0.10 in /home/user/conda/lib/python3.7/site-packages (from matplotlib>=2.0.0->pyannote.metrics>=2.3->pyannote.audio) (0.11.0)\n", "Requirement already satisfied: fonttools>=4.22.0 in /home/user/conda/lib/python3.7/site-packages (from matplotlib>=2.0.0->pyannote.metrics>=2.3->pyannote.audio) (4.28.5)\n", "Requirement already satisfied: llvmlite<0.39,>=0.38.0rc1 in /home/user/conda/lib/python3.7/site-packages (from numba>=0.43.0->librosa>=0.8.0->pyannote.audio) (0.38.0)\n", "Requirement already satisfied: cliff in /home/user/conda/lib/python3.7/site-packages (from optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (3.10.0)\n", "Requirement already satisfied: sqlalchemy>=1.1.0 in /home/user/conda/lib/python3.7/site-packages (from optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (1.3.13)\n", "Requirement already satisfied: alembic in /home/user/conda/lib/python3.7/site-packages (from optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (1.4.1)\n", "Requirement already satisfied: cmaes>=0.8.2 in /home/user/conda/lib/python3.7/site-packages (from optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (0.8.2)\n", "Requirement already satisfied: colorlog in /home/user/conda/lib/python3.7/site-packages (from optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (6.6.0)\n", "Requirement already satisfied: appdirs in /home/user/conda/lib/python3.7/site-packages (from pooch>=1.0->librosa>=0.8.0->pyannote.audio) (1.4.4)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard>=2.0.0->pyannote.audio) (1.25.11)\n", "Requirement already satisfied: idna<2.9,>=2.5 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard>=2.0.0->pyannote.audio) (2.8)\n", "Requirement already satisfied: certifi>=2017.4.17 in /home/user/conda/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard>=2.0.0->pyannote.audio) (2021.10.8)\n", "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard>=2.0.0->pyannote.audio) (3.0.4)\n", "Requirement already satisfied: mpmath>=0.19 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from sympy>=1.1->pyannote.metrics>=2.3->pyannote.audio) (1.2.1)\n", "Requirement already satisfied: click<9.0.0,>=7.1.1 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from typer[all]>=0.2.1->pyannote.database>=4.0->pyannote.audio) (7.1.2)\n", "Requirement already satisfied: colorama<0.5.0,>=0.4.3 in /home/user/conda/lib/python3.7/site-packages (from typer[all]>=0.2.1->pyannote.database>=4.0->pyannote.audio) (0.4.3)\n", "Requirement already satisfied: shellingham<2.0.0,>=1.3.0 in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (from typer[all]>=0.2.1->pyannote.database>=4.0->pyannote.audio) (1.4.0)\n", "Requirement already satisfied: zipp>=0.5 in /home/user/conda/lib/python3.7/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard>=2.0.0->pyannote.audio) (3.7.0)\n", "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /home/user/conda/lib/python3.7/site-packages (from pyasn1-modules>=0.2.1->google-auth<2,>=1.6.3->tensorboard>=2.0.0->pyannote.audio) (0.4.8)\n", "Requirement already satisfied: oauthlib>=3.0.0 in /home/user/conda/lib/python3.7/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=2.0.0->pyannote.audio) (3.1.1)\n", "Requirement already satisfied: python-editor>=0.3 in /home/user/conda/lib/python3.7/site-packages (from alembic->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (1.0.4)\n", "Requirement already satisfied: Mako in /home/user/conda/lib/python3.7/site-packages (from alembic->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (1.1.6)\n", "Requirement already satisfied: pbr!=2.1.0,>=2.0.0 in /home/user/conda/lib/python3.7/site-packages (from cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (5.8.0)\n", "Requirement already satisfied: PrettyTable>=0.7.2 in /home/user/conda/lib/python3.7/site-packages (from cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (3.0.0)\n", "Requirement already satisfied: cmd2>=1.0.0 in /home/user/conda/lib/python3.7/site-packages (from cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (2.3.3)\n", "Requirement already satisfied: stevedore>=2.0.1 in /home/user/conda/lib/python3.7/site-packages (from cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (3.5.0)\n", "Requirement already satisfied: autopage>=0.4.0 in /home/user/conda/lib/python3.7/site-packages (from cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (0.4.0)\n", "Requirement already satisfied: pyperclip>=1.6 in /home/user/conda/lib/python3.7/site-packages (from cmd2>=1.0.0->cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (1.8.2)\n", "Requirement already satisfied: attrs>=16.3.0 in /home/user/conda/lib/python3.7/site-packages (from cmd2>=1.0.0->cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (21.4.0)\n", "Requirement already satisfied: wcwidth>=0.1.7 in /home/user/conda/lib/python3.7/site-packages (from cmd2>=1.0.0->cliff->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (0.2.5)\n", "Requirement already satisfied: MarkupSafe>=0.9.2 in /home/user/conda/lib/python3.7/site-packages (from Mako->alembic->optuna>=1.4->pyannote.pipeline<2.0.0,>=1.5.2->pyannote.audio) (2.0.1)\n", "Requirement already satisfied: pydub in /home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages (0.25.1)\n" ] } ], "source": [ "!pip install pyannote.audio pyannote.core\n", "!pip install pydub" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "id": "YTn33zqvv673" }, "outputs": [], "source": [ "from pyannote.audio.features import RawAudio\n", "from IPython.display import Audio\n", "from sklearn.cluster import KMeans\n", "from pyannote.core import Segment, notebook\n", "import torch" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "id": "16dHYShJfpWT" }, "outputs": [], "source": [ "from pyannote.audio.features import RawAudio\n", "from IPython.display import Audio" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "id": "C43kP6y3wkZe" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Using cache found in /home/jovyan/.cache/torch/hub/pyannote_pyannote-audio_master\n", "Using cache found in /home/jovyan/.cache/torch/hub/pyannote_pyannote-audio_master\n", "Using cache found in /home/jovyan/.cache/torch/hub/pyannote_pyannote-audio_master\n", "Using cache found in /home/jovyan/.cache/torch/hub/pyannote_pyannote-audio_master\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/pyannote/audio/embedding/approaches/arcface_loss.py:170: FutureWarning: The 's' parameter is deprecated in favor of 'scale', and will be removed in a future release\n", " warnings.warn(msg, FutureWarning)\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/pyannote/audio/features/pretrained.py:156: UserWarning: Model was trained with 4s chunks and is applied on 2s chunks. This might lead to sub-optimal results.\n", " warnings.warn(msg)\n", "Using cache found in /home/jovyan/.cache/torch/hub/pyannote_pyannote-audio_master\n" ] } ], "source": [ "device = torch.device(\"cuda\") if torch.cuda.is_available() else torch.device(\"cpu\")\n", "pipeline = torch.hub.load('pyannote/pyannote-audio', 'dia', device=device) #using GPU\n", "\n", "def max_loudness_of_segment(seg, waveform, nmax=1): #determining max volume of a segment\n", " try:\n", " notebook.crop = seg\n", " plot = waveform.crop(seg, return_data=False)\n", " return pd.Series(plot.data.squeeze()).abs().sort_values().tail(nmax).mean()\n", " except Exception as e:\n", " print(e, waveform)\n" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "id": "3NoHuB-Sf305" }, "outputs": [], "source": [ "def diarizator(fpath, speakers): #diarization function\n", " try:\n", " clusterer = KMeans(n_clusters=int(speakers)) \n", " OWN_FILE = {'audio': fpath}\n", " waveform = RawAudio()(OWN_FILE)\n", " # print(waveform)\n", " diarization = pipeline(OWN_FILE)\n", "\n", " segments = list(diarization.itersegments())\n", "\n", " segments_loudnesses_df = pd.Series([max_loudness_of_segment(seg, waveform, 3) for seg in segments])\n", " # clustering by volume: we hypothesise our speakers to have coherent speech volume during the whole rec\n", " # so we distuinguish different speakers based on their speech volume \n", " cluster_ids = clusterer.fit_predict(segments_loudnesses_df.to_numpy().reshape(-1, 1)).tolist() \n", "\n", " diarization_di = diarization.for_json()\n", " for diarization_seg, cluster_id in zip(diarization_di[\"content\"], cluster_ids):\n", " seg_length = diarization_seg[\"segment\"][\"end\"] - diarization_seg[\"segment\"][\"start\"]\n", " label = cluster_id if seg_length > 0.4 else None\n", " diarization_seg[\"label\"] = label\n", " return diarization_di\n", " except Exception as e:\n", " print(e)" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "id": "zuA_isx39gMy", "scrolled": true }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "1260c99041754c77b72e43d98e2e7ce3", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/214 [00:00= n_clusters=3\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "n_samples=3 should be >= n_clusters=4\n", "n_samples=2 should be >= n_clusters=4\n", "n_samples=1 should be >= n_clusters=4\n", "n_samples=2 should be >= n_clusters=3\n", "n_samples=2 should be >= n_clusters=3\n", "n_samples=2 should be >= n_clusters=4\n", "n_samples=3 should be >= n_clusters=4\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "n_samples=2 should be >= n_clusters=3\n", "n_samples=2 should be >= n_clusters=4\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "n_samples=2 should be >= n_clusters=3\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n", "/home/jovyan/.imgenv-oleg-baselines-0/lib/python3.7/site-packages/sklearn/cluster/affinity_propagation_.py:125: UserWarning: All samples have mutually equal similarities. Returning arbitrary cluster center(s).\n", " warnings.warn(\"All samples have mutually equal similarities. \"\n" ] } ], "source": [ "new_df['recognised'] = new_df.progress_apply(lambda x: diarizator(x['file_path'], x['speakers']), axis=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Preparation for evaluation" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "There are very simple metrics here (for preliminary evaluation)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "id": "iFEYKe3x_ur7" }, "outputs": [], "source": [ "def len_source(dictionary):\n", " counter = 0\n", " for i in dictionary:\n", " counter+= len(dictionary[i])\n", " return counter\n", "\n", "def len_regignised(lst):\n", " try:\n", " return len(lst)\n", " except:\n", " return 0\n", "\n", "new_df['segs_source'] = new_df['source_data'].apply(len_source) #counting in source file\n", "new_df['segs_recognised'] = new_df['recognised'].apply(len_regignised) #counting in source file" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "id": "qMgU0ajUA2w-" }, "outputs": [], "source": [ "new_df['distance'] = new_df['segs_source']-new_df['segs_recognised']" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "id": "I4ep53lecllD" }, "outputs": [], "source": [ "def speakers_rec(dictionary):\n", " lst = []\n", " try:\n", " for i in dictionary:\n", " for j in i:\n", " if j == 'label':\n", " lst.append(i[j])\n", " return len(set(lst))\n", " except:\n", " return 0\n", "new_df['speakers_rec'] = new_df['recognised'].apply(speakers_rec) " ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "id": "UJUJwsfrhawE" }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
file_pathsource_dataspeakersrecognisedsegs_sourcesegs_recogniseddistancespeakers_recspeaker_distance
0./audio_to_release/yrk/es100708_MatjPelaNEN.WA...{'F2': {1: [48.95399999999999, 49.525]}}1{'pyannote': 'Annotation', 'content': [{'segme...13-201
1./audio_to_release/yrk/TOYa_audio_TNenets.wav.wav{'АМК': {1: [0.2339999999999999, 5.186], 2: [5...1{'pyannote': 'Annotation', 'content': [{'segme...1531201
2./audio_to_release/sah/game_1-885s-2-1.mp4.wav{'1': {1: [21.613000000000003, 22.44], 2: [24....4{'pyannote': 'Annotation', 'content': [{'segme...1431104
3./audio_to_release/sah/game_1-885s-0-3.mp4.wav{'1': {1: [21.248999999999995, 23.116999999999...4{'pyannote': 'Annotation', 'content': [{'segme...1431104
4./audio_to_release/sah/game_1-885s-2-6.mp4.wav{'2': {1: [21.80500000000001, 22.4049999999999...4{'pyannote': 'Annotation', 'content': [{'segme...1731404
..............................
209./audio_to_release/mhr/mhr_rus-StTor-100118-AN...{'anf': {1: [16.185999999999922, 23.8579999999...1{'pyannote': 'Annotation', 'content': [{'segme...43101
210./audio_to_release/mhr/mhr_rus-StTor-100118-AN...{'anf': {1: [23.43699999999989, 25.19499999999...2{'pyannote': 'Annotation', 'content': [{'segme...53202
211./audio_to_release/mhr/mhr_rus-StTor-100118-AN...{'anf': {1: [19.65799999999989, 23.86899999999...2{'pyannote': 'Annotation', 'content': [{'segme...73402
212./audio_to_release/mhr/mhr_rus-StTor-100118-AN...{'anf': {1: [20.497000000000067, 25.3640000000...2{'pyannote': 'Annotation', 'content': [{'segme...33002
213./audio_to_release/mhr/mhr_rus-StTor-100118-AN...{'zvk': {1: [17.308999999999973, 24.5930000000...2{'pyannote': 'Annotation', 'content': [{'segme...83502
\n", "

214 rows × 9 columns

\n", "
" ], "text/plain": [ " file_path \\\n", "0 ./audio_to_release/yrk/es100708_MatjPelaNEN.WA... \n", "1 ./audio_to_release/yrk/TOYa_audio_TNenets.wav.wav \n", "2 ./audio_to_release/sah/game_1-885s-2-1.mp4.wav \n", "3 ./audio_to_release/sah/game_1-885s-0-3.mp4.wav \n", "4 ./audio_to_release/sah/game_1-885s-2-6.mp4.wav \n", ".. ... \n", "209 ./audio_to_release/mhr/mhr_rus-StTor-100118-AN... \n", "210 ./audio_to_release/mhr/mhr_rus-StTor-100118-AN... \n", "211 ./audio_to_release/mhr/mhr_rus-StTor-100118-AN... \n", "212 ./audio_to_release/mhr/mhr_rus-StTor-100118-AN... \n", "213 ./audio_to_release/mhr/mhr_rus-StTor-100118-AN... \n", "\n", " source_data speakers \\\n", "0 {'F2': {1: [48.95399999999999, 49.525]}} 1 \n", "1 {'АМК': {1: [0.2339999999999999, 5.186], 2: [5... 1 \n", "2 {'1': {1: [21.613000000000003, 22.44], 2: [24.... 4 \n", "3 {'1': {1: [21.248999999999995, 23.116999999999... 4 \n", "4 {'2': {1: [21.80500000000001, 22.4049999999999... 4 \n", ".. ... ... \n", "209 {'anf': {1: [16.185999999999922, 23.8579999999... 1 \n", "210 {'anf': {1: [23.43699999999989, 25.19499999999... 2 \n", "211 {'anf': {1: [19.65799999999989, 23.86899999999... 2 \n", "212 {'anf': {1: [20.497000000000067, 25.3640000000... 2 \n", "213 {'zvk': {1: [17.308999999999973, 24.5930000000... 2 \n", "\n", " recognised segs_source \\\n", "0 {'pyannote': 'Annotation', 'content': [{'segme... 1 \n", "1 {'pyannote': 'Annotation', 'content': [{'segme... 15 \n", "2 {'pyannote': 'Annotation', 'content': [{'segme... 14 \n", "3 {'pyannote': 'Annotation', 'content': [{'segme... 14 \n", "4 {'pyannote': 'Annotation', 'content': [{'segme... 17 \n", ".. ... ... \n", "209 {'pyannote': 'Annotation', 'content': [{'segme... 4 \n", "210 {'pyannote': 'Annotation', 'content': [{'segme... 5 \n", "211 {'pyannote': 'Annotation', 'content': [{'segme... 7 \n", "212 {'pyannote': 'Annotation', 'content': [{'segme... 3 \n", "213 {'pyannote': 'Annotation', 'content': [{'segme... 8 \n", "\n", " segs_recognised distance speakers_rec speaker_distance \n", "0 3 -2 0 1 \n", "1 3 12 0 1 \n", "2 3 11 0 4 \n", "3 3 11 0 4 \n", "4 3 14 0 4 \n", ".. ... ... ... ... \n", "209 3 1 0 1 \n", "210 3 2 0 2 \n", "211 3 4 0 2 \n", "212 3 0 0 2 \n", "213 3 5 0 2 \n", "\n", "[214 rows x 9 columns]" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "new_df['speaker_distance'] = new_df['speakers']-new_df['speakers_rec'] #distance between the number of speakers\n", "new_df" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "id": "CAtFIXegh7lx" }, "outputs": [], "source": [ "new_df.to_csv('diarization.csv')" ] }, { "cell_type": "markdown", "metadata": { "id": "eq8AkBjQie5l" }, "source": [ "# Evaluation results" ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 592 }, "id": "54FewqkniiAO", "outputId": "a7674439-014c-4710-91c1-37149610fdb4" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "x = [list(new_df['distance'].values),\n", " list(new_df['speaker_distance'].values)]\n", "df = pd.DataFrame(x, index=['Distance in the number of segments', 'Distance in the number of speakers'])\n", "\n", "\n", "df.T.boxplot(vert=False, figsize=(20,10))\n", "plt.subplots_adjust(left=0.25)\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "colab": { "collapsed_sections": [ "lk3JBaGyTzYU" ], "name": "diarization.ipynb", "provenance": [], "toc_visible": true }, "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.12" } }, "nbformat": 4, "nbformat_minor": 1 }