{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "399bcf00", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Hit:1 http://archive.ubuntu.com/ubuntu xenial InRelease\n", "Get:2 http://archive.ubuntu.com/ubuntu xenial-updates InRelease [99.8 kB] \u001b[0m\n", "Get:4 http://archive.ubuntu.com/ubuntu xenial-backports InRelease [97.4 kB]0m \u001b[0m\u001b[33m\u001b[33m\n", "Err:3 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease3m\n", " The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC\n", "Get:5 http://security.ubuntu.com/ubuntu xenial-security InRelease [99.8 kB]\n", "Ign:6 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64 InRelease\n", "Hit:7 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64 Release\n", "Reading package lists... Done\u001b[0m \u001b[0m \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n", "W: GPG error: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC\n", "E: The repository 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease' is not signed.\n", "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n", "N: See apt-secure(8) manpage for repository creation and user configuration details.\n", "Reading package lists... Done\n", "Building dependency tree \n", "Reading state information... Done\n", "ffmpeg is already the newest version (7:2.8.17-0ubuntu0.1).\n", "0 upgraded, 0 newly installed, 0 to remove and 23 not upgraded.\n" ] } ], "source": [ "!apt update\n", "!apt -y install ffmpeg" ] }, { "cell_type": "code", "execution_count": 2, "id": "a1556690", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2022-06-02 07:02:00-- https://files.deeppavlov.ai/field-matters/releases/demo/asr_data.csv\n", "Resolving files.deeppavlov.ai (files.deeppavlov.ai)... 10.11.1.254\n", "Connecting to files.deeppavlov.ai (files.deeppavlov.ai)|10.11.1.254|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 334717 (327K) [application/octet-stream]\n", "Saving to: ‘asr_data.csv’\n", "\n", "asr_data.csv 100%[===================>] 326.87K --.-KB/s in 0.02s \n", "\n", "2022-06-02 07:02:01 (16.3 MB/s) - ‘asr_data.csv’ saved [334717/334717]\n", "\n", "--2022-06-02 07:02:01-- https://files.deeppavlov.ai/field-matters/releases/demo/sound.zip\n", "Resolving files.deeppavlov.ai (files.deeppavlov.ai)... 10.11.1.254\n", "Connecting to files.deeppavlov.ai (files.deeppavlov.ai)|10.11.1.254|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 1198165394 (1.1G) [application/zip]\n", "Saving to: ‘sound.zip’\n", "\n", "sound.zip 100%[===================>] 1.12G 260MB/s in 4.9s \n", "\n", "2022-06-02 07:02:06 (235 MB/s) - ‘sound.zip’ saved [1198165394/1198165394]\n", "\n", "Archive: sound.zip\n", " creating: audio_to_release/\n", " creating: audio_to_release/ckt/\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", " creating: audio_to_release/evn/\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", " creating: audio_to_release/mhr/\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", " creating: audio_to_release/sah/\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", " creating: audio_to_release/yrk/\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/asr_data.csv\n", "!wget -c https://files.deeppavlov.ai/field-matters/releases/demo/sound.zip\n", "!unzip sound.zip" ] }, { "cell_type": "code", "execution_count": 3, "id": "36ce690a", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import os\n", "import re\n", "from tqdm.auto import tqdm\n", "tqdm.pandas()" ] }, { "cell_type": "code", "execution_count": 11, "id": "80ea3394", "metadata": {}, "outputs": [], "source": [ "df = pd.read_csv('asr_data.csv') #your dataset here" ] }, { "cell_type": "code", "execution_count": 12, "id": "1c36b3cb", "metadata": {}, "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", "
startendtranscriptionsourcelangfpath
04.2607.113«Myaryosiw tina (Myaryosiw ti),es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
17.1169.642sawa nyeǣǣy (săwă nye).es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
216.63819.785Pada ni yutʃitʹq (Pida ni yusidaq),es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
319.78722.974pirye yesyada tănya (pirye yesyada tănya).es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
494.89397.867Săwawna macraaa (săwawna măncara),es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
.....................
320728.47629.481gunən.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
320829.90233.549ēlā əto ēlā bəjə odantə̄.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
320934.54838.193a əto bəjəl gunďərəØ.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
321039.22140.906ŋinakin əmərən.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
321140.90642.397gu= gučōn tug.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
\n", "

3212 rows × 6 columns

\n", "
" ], "text/plain": [ " start end transcription \\\n", "0 4.260 7.113 «Myaryosiw tina (Myaryosiw ti), \n", "1 7.116 9.642 sawa nyeǣǣy (săwă nye). \n", "2 16.638 19.785 Pada ni yutʃitʹq (Pida ni yusidaq), \n", "3 19.787 22.974 pirye yesyada tănya (pirye yesyada tănya). \n", "4 94.893 97.867 Săwawna macraaa (săwawna măncara), \n", "... ... ... ... \n", "3207 28.476 29.481 gunən. \n", "3208 29.902 33.549 ēlā əto ēlā bəjə odantə̄. \n", "3209 34.548 38.193 a əto bəjəl gunďərəØ. \n", "3210 39.221 40.906 ŋinakin əmərən. \n", "3211 40.906 42.397 gu= gučōn tug. \n", "\n", " source lang \\\n", "0 es100708_MatjPelaNEN.WAV yrk \n", "1 es100708_MatjPelaNEN.WAV yrk \n", "2 es100708_MatjPelaNEN.WAV yrk \n", "3 es100708_MatjPelaNEN.WAV yrk \n", "4 es100708_MatjPelaNEN.WAV yrk \n", "... ... ... \n", "3207 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3208 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3209 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3210 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3211 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "\n", " fpath \n", "0 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "1 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "2 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "3 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "4 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "... ... \n", "3207 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3208 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3209 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3210 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3211 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "\n", "[3212 rows x 6 columns]" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"fpath\"] = './audio_to_release/' + df[\"lang\"].astype(str) + \"/\" + df[\"source\"].astype(str)\n", "df" ] }, { "cell_type": "code", "execution_count": 13, "id": "6e6cfea9", "metadata": {}, "outputs": [], "source": [ "#adding paths to file to dataset\n", "df[\"fpath\"] = './audio_to_release/' + df[\"lang\"].astype(str) + \"/\" + df[\"source\"].astype(str)\n", "#removing spaces in dataset's paths\n", "cache = {}\n", "def fix_path(path):\n", " try:\n", " new_path = path.replace(' ', '_')\n", " new_path = cache.setdefault(path, new_path)\n", " if not os.path.exists(new_path):\n", " os.rename(path, new_path)\n", " return new_path\n", " except Exception as e:\n", " print(e)\n", "df['fpath'] = df['fpath'].apply(fix_path)\n", "\n", "df = df.reset_index() #adding indexes(id)" ] }, { "cell_type": "code", "execution_count": 14, "id": "1490b7c9", "metadata": {}, "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", "
level_0indexstartendtranscriptionsourcelangfpath
0004.2607.113«Myaryosiw tina (Myaryosiw ti),es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
1117.1169.642sawa nyeǣǣy (săwă nye).es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
22216.63819.785Pada ni yutʃitʹq (Pida ni yusidaq),es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
33319.78722.974pirye yesyada tănya (pirye yesyada tănya).es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
44494.89397.867Săwawna macraaa (săwawna măncara),es100708_MatjPelaNEN.WAVyrk./audio_to_release/yrk/es100708_MatjPelaNEN.WAV
...........................
32073207320728.47629.481gunən.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
32083208320829.90233.549ēlā əto ēlā bəjə odantə̄.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
32093209320934.54838.193a əto bəjəl gunďərəØ.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
32103210321039.22140.906ŋinakin əmərən.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
32113211321140.90642.397gu= gučōn tug.2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2...evn./audio_to_release/evn/2011_Potapovo_Bogdanova...
\n", "

3212 rows × 8 columns

\n", "
" ], "text/plain": [ " level_0 index start end \\\n", "0 0 0 4.260 7.113 \n", "1 1 1 7.116 9.642 \n", "2 2 2 16.638 19.785 \n", "3 3 3 19.787 22.974 \n", "4 4 4 94.893 97.867 \n", "... ... ... ... ... \n", "3207 3207 3207 28.476 29.481 \n", "3208 3208 3208 29.902 33.549 \n", "3209 3209 3209 34.548 38.193 \n", "3210 3210 3210 39.221 40.906 \n", "3211 3211 3211 40.906 42.397 \n", "\n", " transcription \\\n", "0 «Myaryosiw tina (Myaryosiw ti), \n", "1 sawa nyeǣǣy (săwă nye). \n", "2 Pada ni yutʃitʹq (Pida ni yusidaq), \n", "3 pirye yesyada tănya (pirye yesyada tănya). \n", "4 Săwawna macraaa (săwawna măncara), \n", "... ... \n", "3207 gunən. \n", "3208 ēlā əto ēlā bəjə odantə̄. \n", "3209 a əto bəjəl gunďərəØ. \n", "3210 ŋinakin əmərən. \n", "3211 gu= gučōn tug. \n", "\n", " source lang \\\n", "0 es100708_MatjPelaNEN.WAV yrk \n", "1 es100708_MatjPelaNEN.WAV yrk \n", "2 es100708_MatjPelaNEN.WAV yrk \n", "3 es100708_MatjPelaNEN.WAV yrk \n", "4 es100708_MatjPelaNEN.WAV yrk \n", "... ... ... \n", "3207 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3208 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3209 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3210 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "3211 2011_Potapovo_Bogdanova_Tamara_Andreevna_FM2-2... evn \n", "\n", " fpath \n", "0 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "1 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "2 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "3 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "4 ./audio_to_release/yrk/es100708_MatjPelaNEN.WAV \n", "... ... \n", "3207 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3208 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3209 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3210 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "3211 ./audio_to_release/evn/2011_Potapovo_Bogdanova... \n", "\n", "[3212 rows x 8 columns]" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def replacer(path):\n", " return path.replace(' ', '_')\n", "df['fpath'] = df['fpath'].apply(replacer)\n", "df = df.reset_index() #adding indexes(id)\n", "df" ] }, { "cell_type": "code", "execution_count": 15, "id": "aba69eef", "metadata": {}, "outputs": [], "source": [ "new_dir = './new_audio' #new directory for cut files\n", "if os.path.exists(new_dir) is False:\n", " os.mkdir(new_dir)\n", "else:\n", " print('folder already exists')" ] }, { "cell_type": "code", "execution_count": 16, "id": "d4de1591", "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "7be4af833e8e4fde8c69eb872b6afc72", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/3212 [00:00 ffmpeg_log/{index}.log\n", "\n", " \n", "df.progress_apply(cutter, axis=1)" ] }, { "cell_type": "code", "execution_count": 17, "id": "d93919e0", "metadata": {}, "outputs": [], "source": [ "#making column for paths of cut files\n", "df['new_path'] = df['index'].apply(lambda x: './new_audio/' + str(x) + '.wav')" ] }, { "cell_type": "markdown", "id": "e17260ba", "metadata": {}, "source": [ "# ASR" ] }, { "cell_type": "code", "execution_count": 18, "id": "29ccfeec", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Hit:1 http://archive.ubuntu.com/ubuntu xenial InRelease\n", "Hit:2 http://archive.ubuntu.com/ubuntu xenial-updates InRelease \u001b[0m\n", "Hit:3 http://archive.ubuntu.com/ubuntu xenial-backports InRelease \u001b[0m\n", "Hit:4 http://security.ubuntu.com/ubuntu xenial-security InRelease \u001b[33m\n", "Get:5 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease [1,581 B]\n", "Ign:6 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64 InRelease\n", "Err:5 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease\n", " The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC\n", "Hit:7 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64 Release\n", "Reading package lists... Done[0m\u001b[33m\n", "W: GPG error: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC\n", "E: The repository 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 InRelease' is not signed.\n", "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n", "N: See apt-secure(8) manpage for repository creation and user configuration details.\n", "Requirement already satisfied: transformers in ./venv/lib/python3.7/site-packages (4.19.2)\n", "Requirement already satisfied: datasets in ./venv/lib/python3.7/site-packages (2.2.2)\n", "Requirement already satisfied: phonemizer in ./venv/lib/python3.7/site-packages (3.2.0)\n", "Requirement already satisfied: numpy>=1.17 in ./venv/lib/python3.7/site-packages/numpy-1.18.0-py3.7-linux-x86_64.egg (from transformers) (1.18.0)\n", "Requirement already satisfied: importlib-metadata in ./venv/lib/python3.7/site-packages (from transformers) (4.4.0)\n", "Requirement already satisfied: tokenizers!=0.11.3,<0.13,>=0.11.1 in ./venv/lib/python3.7/site-packages (from transformers) (0.12.1)\n", "Requirement already satisfied: tqdm>=4.27 in ./venv/lib/python3.7/site-packages (from transformers) (4.64.0)\n", "Requirement already satisfied: huggingface-hub<1.0,>=0.1.0 in ./venv/lib/python3.7/site-packages (from transformers) (0.7.0)\n", "Requirement already satisfied: filelock in ./venv/lib/python3.7/site-packages/filelock-3.0.12-py3.7.egg (from transformers) (3.0.12)\n", "Requirement already satisfied: packaging>=20.0 in ./venv/lib/python3.7/site-packages (from transformers) (21.3)\n", "Requirement already satisfied: regex!=2019.12.17 in ./venv/lib/python3.7/site-packages (from transformers) (2022.3.15)\n", "Requirement already satisfied: pyyaml>=5.1 in ./venv/lib/python3.7/site-packages (from transformers) (6.0)\n", "Requirement already satisfied: requests in ./venv/lib/python3.7/site-packages/requests-2.22.0-py3.7.egg (from transformers) (2.22.0)\n", "Requirement already satisfied: responses<0.19 in ./venv/lib/python3.7/site-packages (from datasets) (0.18.0)\n", "Requirement already satisfied: xxhash in ./venv/lib/python3.7/site-packages (from datasets) (3.0.0)\n", "Requirement already satisfied: pyarrow>=6.0.0 in ./venv/lib/python3.7/site-packages (from datasets) (8.0.0)\n", "Requirement already satisfied: pandas in ./venv/lib/python3.7/site-packages/pandas-0.25.3-py3.7-linux-x86_64.egg (from datasets) (0.25.3)\n", "Requirement already satisfied: fsspec[http]>=2021.05.0 in ./venv/lib/python3.7/site-packages (from datasets) (2022.5.0)\n", "Requirement already satisfied: dill<0.3.5 in ./venv/lib/python3.7/site-packages (from datasets) (0.3.4)\n", "Requirement already satisfied: multiprocess in ./venv/lib/python3.7/site-packages (from datasets) (0.70.12.2)\n", "Requirement already satisfied: aiohttp in ./venv/lib/python3.7/site-packages (from datasets) (3.8.1)\n", "Requirement already satisfied: attrs>=18.1 in ./venv/lib/python3.7/site-packages (from phonemizer) (21.2.0)\n", "Requirement already satisfied: typing-extensions in ./venv/lib/python3.7/site-packages/typing_extensions-3.10.0.0-py3.7.egg (from phonemizer) (3.10.0.0)\n", "Requirement already satisfied: dlinfo in ./venv/lib/python3.7/site-packages (from phonemizer) (1.2.1)\n", "Requirement already satisfied: segments in ./venv/lib/python3.7/site-packages (from phonemizer) (2.2.0)\n", "Requirement already satisfied: joblib in ./venv/lib/python3.7/site-packages/joblib-1.0.1-py3.7.egg (from phonemizer) (1.0.1)\n", "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in ./venv/lib/python3.7/site-packages (from packaging>=20.0->transformers) (3.0.6)\n", "Requirement already satisfied: certifi>=2017.4.17 in ./venv/lib/python3.7/site-packages/certifi-2021.5.30-py3.7.egg (from requests->transformers) (2021.5.30)\n", "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in ./venv/lib/python3.7/site-packages/chardet-3.0.4-py3.7.egg (from requests->transformers) (3.0.4)\n", "Requirement already satisfied: idna<2.9,>=2.5 in ./venv/lib/python3.7/site-packages/idna-2.8-py3.7.egg (from requests->transformers) (2.8)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in ./venv/lib/python3.7/site-packages/urllib3-1.25.11-py3.7.egg (from requests->transformers) (1.25.11)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./venv/lib/python3.7/site-packages (from aiohttp->datasets) (4.0.2)\n", "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./venv/lib/python3.7/site-packages (from aiohttp->datasets) (2.0.12)\n", "Requirement already satisfied: frozenlist>=1.1.1 in ./venv/lib/python3.7/site-packages (from aiohttp->datasets) (1.3.0)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in ./venv/lib/python3.7/site-packages/yarl-1.6.3-py3.7-linux-x86_64.egg (from aiohttp->datasets) (1.6.3)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in ./venv/lib/python3.7/site-packages/multidict-5.1.0-py3.7-linux-x86_64.egg (from aiohttp->datasets) (5.1.0)\n", "Requirement already satisfied: aiosignal>=1.1.2 in ./venv/lib/python3.7/site-packages (from aiohttp->datasets) (1.2.0)\n", "Requirement already satisfied: asynctest==0.13.0 in ./venv/lib/python3.7/site-packages (from aiohttp->datasets) (0.13.0)\n", "Requirement already satisfied: zipp>=0.5 in ./venv/lib/python3.7/site-packages (from importlib-metadata->transformers) (3.4.1)\n", "Requirement already satisfied: python-dateutil>=2.6.1 in ./venv/lib/python3.7/site-packages/python_dateutil-2.8.1-py3.7.egg (from pandas->datasets) (2.8.1)\n", "Requirement already satisfied: pytz>=2017.2 in ./venv/lib/python3.7/site-packages/pytz-2019.1-py3.7.egg (from pandas->datasets) (2019.1)\n", "Requirement already satisfied: clldutils>=1.7.3 in ./venv/lib/python3.7/site-packages (from segments->phonemizer) (3.12.0)\n", "Requirement already satisfied: csvw>=1.5.6 in ./venv/lib/python3.7/site-packages (from segments->phonemizer) (2.0.0)\n", "Requirement already satisfied: tabulate>=0.7.7 in ./venv/lib/python3.7/site-packages (from clldutils>=1.7.3->segments->phonemizer) (0.8.9)\n", "Requirement already satisfied: colorlog in ./venv/lib/python3.7/site-packages (from clldutils>=1.7.3->segments->phonemizer) (6.6.0)\n", "Requirement already satisfied: isodate in ./venv/lib/python3.7/site-packages (from csvw>=1.5.6->segments->phonemizer) (0.6.1)\n", "Requirement already satisfied: rfc3986<2 in ./venv/lib/python3.7/site-packages (from csvw>=1.5.6->segments->phonemizer) (1.5.0)\n", "Requirement already satisfied: uritemplate>=3.0.0 in ./venv/lib/python3.7/site-packages (from csvw>=1.5.6->segments->phonemizer) (4.1.1)\n", "Requirement already satisfied: six>=1.5 in ./venv/lib/python3.7/site-packages/six-1.16.0-py3.7.egg (from python-dateutil>=2.6.1->pandas->datasets) (1.16.0)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "Reading package lists... Done\n", "Building dependency tree \n", "Reading state information... Done\n", "espeak is already the newest version (1.48.04+dfsg-2).\n", "0 upgraded, 0 newly installed, 0 to remove and 23 not upgraded.\n", "Requirement already satisfied: pydub in ./venv/lib/python3.7/site-packages (0.25.1)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "\u001b[0mRequirement already satisfied: transformers in ./venv/lib/python3.7/site-packages (4.19.2)\n", "Requirement already satisfied: regex!=2019.12.17 in ./venv/lib/python3.7/site-packages (from transformers) (2022.3.15)\n", "Requirement already satisfied: huggingface-hub<1.0,>=0.1.0 in ./venv/lib/python3.7/site-packages (from transformers) (0.7.0)\n", "Requirement already satisfied: tqdm>=4.27 in ./venv/lib/python3.7/site-packages (from transformers) (4.64.0)\n", "Requirement already satisfied: requests in ./venv/lib/python3.7/site-packages/requests-2.22.0-py3.7.egg (from transformers) (2.22.0)\n", "Requirement already satisfied: pyyaml>=5.1 in ./venv/lib/python3.7/site-packages (from transformers) (6.0)\n", "Requirement already satisfied: importlib-metadata in ./venv/lib/python3.7/site-packages (from transformers) (4.4.0)\n", "Requirement already satisfied: tokenizers!=0.11.3,<0.13,>=0.11.1 in ./venv/lib/python3.7/site-packages (from transformers) (0.12.1)\n", "Requirement already satisfied: numpy>=1.17 in ./venv/lib/python3.7/site-packages/numpy-1.18.0-py3.7-linux-x86_64.egg (from transformers) (1.18.0)\n", "Requirement already satisfied: filelock in ./venv/lib/python3.7/site-packages/filelock-3.0.12-py3.7.egg (from transformers) (3.0.12)\n", "Requirement already satisfied: packaging>=20.0 in ./venv/lib/python3.7/site-packages (from transformers) (21.3)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./venv/lib/python3.7/site-packages/typing_extensions-3.10.0.0-py3.7.egg (from huggingface-hub<1.0,>=0.1.0->transformers) (3.10.0.0)\n", "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in ./venv/lib/python3.7/site-packages (from packaging>=20.0->transformers) (3.0.6)\n", "Requirement already satisfied: zipp>=0.5 in ./venv/lib/python3.7/site-packages (from importlib-metadata->transformers) (3.4.1)\n", "Requirement already satisfied: certifi>=2017.4.17 in ./venv/lib/python3.7/site-packages/certifi-2021.5.30-py3.7.egg (from requests->transformers) (2021.5.30)\n", "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in ./venv/lib/python3.7/site-packages/chardet-3.0.4-py3.7.egg (from requests->transformers) (3.0.4)\n", "Requirement already satisfied: idna<2.9,>=2.5 in ./venv/lib/python3.7/site-packages/idna-2.8-py3.7.egg (from requests->transformers) (2.8)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in ./venv/lib/python3.7/site-packages/urllib3-1.25.11-py3.7.egg (from requests->transformers) (1.25.11)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "\u001b[0mRequirement already satisfied: torchaudio in ./venv/lib/python3.7/site-packages (0.11.0)\n", "Requirement already satisfied: torch==1.11.0 in ./venv/lib/python3.7/site-packages (from torchaudio) (1.11.0)\n", "Requirement already satisfied: typing-extensions in ./venv/lib/python3.7/site-packages/typing_extensions-3.10.0.0-py3.7.egg (from torch==1.11.0->torchaudio) (3.10.0.0)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "\u001b[0mRequirement already satisfied: tqdm in ./venv/lib/python3.7/site-packages (4.64.0)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "\u001b[0mRequirement already satisfied: torchaudio in ./venv/lib/python3.7/site-packages (0.11.0)\n", "Requirement already satisfied: torch==1.11.0 in ./venv/lib/python3.7/site-packages (from torchaudio) (1.11.0)\n", "Requirement already satisfied: typing-extensions in ./venv/lib/python3.7/site-packages/typing_extensions-3.10.0.0-py3.7.egg (from torch==1.11.0->torchaudio) (3.10.0.0)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "\u001b[0m" ] } ], "source": [ "!apt update\n", "!pip install transformers datasets phonemizer\n", "!apt install espeak\n", "!pip install pydub\n", "!pip install transformers --upgrade\n", "!pip install torchaudio\n", "!pip install tqdm --upgrade\n", "!pip install torchaudio --upgrade" ] }, { "cell_type": "code", "execution_count": 19, "id": "3147d191", "metadata": {}, "outputs": [], "source": [ "from tqdm import auto" ] }, { "cell_type": "code", "execution_count": 20, "id": "ba047513", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "transformers_ver:\t4.19.2\n", "tqdm_ver:\t4.64.0\n", "torch_ver:\t1.11.0+cu102\n", "torchaudio_ver:\t0.11.0+cu102\n", "pandas_ver:\t0.25.3\n" ] } ], "source": [ "from transformers import __version__ as transformers_ver\n", "from tqdm import __version__ as tqdm_ver\n", "from torch import __version__ as torch_ver\n", "from torchaudio import __version__ as torchaudio_ver\n", "from pandas import __version__ as pd_ver\n", "print(f\"transformers_ver:\\t{transformers_ver}\")\n", "print(f\"tqdm_ver:\\t{tqdm_ver}\")\n", "print(f\"torch_ver:\\t{torch_ver}\")\n", "print(f\"torchaudio_ver:\\t{torchaudio_ver}\")\n", "print(f\"pandas_ver:\\t{pd_ver}\")" ] }, { "cell_type": "code", "execution_count": 21, "id": "310c2b74", "metadata": { "scrolled": true }, "outputs": [], "source": [ "from transformers import AutoModelForCTC, Wav2Vec2Processor\n", "\n", "model = AutoModelForCTC.from_pretrained(\"facebook/wav2vec2-xlsr-53-espeak-cv-ft\")\n", "processor = Wav2Vec2Processor.from_pretrained(\"facebook/wav2vec2-xlsr-53-espeak-cv-ft\")" ] }, { "cell_type": "code", "execution_count": 22, "id": "bb8af507", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Thu Jun 2 07:50:42 2022 \n", "+-----------------------------------------------------------------------------+\n", "| NVIDIA-SMI 495.46 Driver Version: 495.46 CUDA Version: 11.5 |\n", "|-------------------------------+----------------------+----------------------+\n", "| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n", "| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n", "| | | MIG M. |\n", "|===============================+======================+======================|\n", "| 6 NVIDIA GeForce ... Off | 00000000:0C:00.0 Off | N/A |\n", "| 23% 23C P8 7W / 250W | 3503MiB / 11178MiB | 0% Default |\n", "| | | N/A |\n", "+-------------------------------+----------------------+----------------------+\n", " \n", "+-----------------------------------------------------------------------------+\n", "| Processes: |\n", "| GPU GI CI PID Type Process name GPU Memory |\n", "| ID ID Usage |\n", "|=============================================================================|\n", "+-----------------------------------------------------------------------------+\n" ] } ], "source": [ "import os; cuda_num = os.getenv(\"CUDA_VISIBLE_DEVICES\")\n", "\n", "!nvidia-smi -i {cuda_num}" ] }, { "cell_type": "code", "execution_count": 23, "id": "647e7c97", "metadata": {}, "outputs": [], "source": [ "import torch\n", "import torchaudio\n", "from tqdm.auto import tqdm\n", "tqdm.pandas()\n", "device = torch.device(f\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", "\n", "model = model.to(device)\n", "\n", "def recognizer(fpath):\n", " try:\n", " waveform, sample_rate = torchaudio.load(fpath)\n", " waveform = waveform.to(device)\n", " logits = model(waveform).logits\n", " pred_ids = torch.argmax(logits, dim=-1)\n", " pred_str = processor.batch_decode(pred_ids)[0]\n", " return pred_str\n", " except:\n", " return 0" ] }, { "cell_type": "code", "execution_count": 24, "id": "07949fda", "metadata": { "scrolled": false }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "3c81f6a6603d495fa99a898e453845e6", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/3212 [00:00\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", "
transcriptionrecognized
1544ănyanaǣwaki?niː
42Tamălyaŋgănanyerdyenyaŋăcyekiamnɲeːdnmaske
1401Irinimyadhnyanaanaw.iːriːɡmeːneːna
2904umnōbiguləkōndūjibiďə munnobiɡulokanobiɟo
2359dundəhərgīdōlīnďudukinuləsəlďudukinjūwjūwkōtta...nodarɡidalindokindasauːdinɲuːkkatatidʊnddudask...
1071nyenǣcyahŋămcaawyathŋăwărwuniŋaq»dʒantat
1839qəqəmjarkəpɬətkə...aqəqəmjarkəpɬatɣeqqabjarqabθqaqaːqamjaːrkplak
1036păromlasyǎtidaalaʃt
2722ēkunəsundūgunďəmənəaksapkānaeːkonfnduːqudunbaːlsatkan
3067učastoknunadvoihnud'ukčand'ukčadūtʃasɛknəlabdlʊktʃəjʊktʃəl
\n", "" ], "text/plain": [ " transcription \\\n", "1544 ănyanaǣwaki? \n", "42 Tamălyaŋgănanyerdyenyaŋăcyeki \n", "1401 Irinimyadhnyanaanaw. \n", "2904 umnōbiguləkōndūjibiďə m \n", "2359 dundəhərgīdōlīnďudukinuləsəlďudukinjūwjūwkōtta... \n", "1071 nyenǣcyahŋămcaawyathŋăwărwuniŋaq» \n", "1839 qəqəmjarkəpɬətkə...aqəqəmjarkəpɬatɣe \n", "1036 păromlasyǎtida \n", "2722 ēkunəsundūgunďəmənəaksapkāna \n", "3067 učastoknunadvoihnud'ukčand'ukčadū \n", "\n", " recognized \n", "1544 niː \n", "42 amnɲeːdnmaske \n", "1401 iːriːɡmeːneːna \n", "2904 unnobiɡulokanobiɟo \n", "2359 nodarɡidalindokindasauːdinɲuːkkatatidʊnddudask... \n", "1071 dʒantat \n", "1839 qqabjarqabθqaqaːqamjaːrkplak \n", "1036 alaʃt \n", "2722 eːkonfnduːqudunbaːlsatkan \n", "3067 tʃasɛknəlabdlʊktʃəjʊktʃəl " ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[[\"transcription\", \"recognized\"]].sample(10)" ] }, { "cell_type": "markdown", "id": "f1582028", "metadata": {}, "source": [ "# Evaluation" ] }, { "cell_type": "code", "execution_count": 29, "id": "b9a7e458", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: abydos in ./venv/lib/python3.7/site-packages (0.5.0)\n", "Requirement already satisfied: deprecation in ./venv/lib/python3.7/site-packages (from abydos) (2.1.0)\n", "Requirement already satisfied: numpy in ./venv/lib/python3.7/site-packages/numpy-1.18.0-py3.7-linux-x86_64.egg (from abydos) (1.18.0)\n", "Requirement already satisfied: packaging in ./venv/lib/python3.7/site-packages (from deprecation->abydos) (21.3)\n", "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in ./venv/lib/python3.7/site-packages (from packaging->deprecation->abydos) (3.0.6)\n", "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.\n", "You should consider upgrading via the '/base/venv/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n", "\u001b[0m" ] } ], "source": [ "!pip install abydos" ] }, { "cell_type": "code", "execution_count": 30, "id": "c98120e3", "metadata": {}, "outputs": [], "source": [ "from abydos import distance" ] }, { "cell_type": "code", "execution_count": 31, "id": "79d373eb", "metadata": {}, "outputs": [], "source": [ "phonetic = distance.PhoneticEditDistance()" ] }, { "cell_type": "code", "execution_count": 34, "id": "4e65ec5e", "metadata": {}, "outputs": [], "source": [ "phonetic = distance.PhoneticEditDistance()\n", "def phonetic_metric(row):\n", " try:\n", " result = phonetic.dist(row['transcription'], row['recognized'])\n", " return result\n", " except Exception as e:\n", " print(e)" ] }, { "cell_type": "code", "execution_count": 36, "id": "d95f9cb3", "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "7bc1325861cf48768dc381ad1b0d091e", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/3212 [00:00\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", "
transcriptionrecognizedphonetic_ev
2085bəjunməńanətontukpəktirōrəpadratbojuːmaɲanatontpuktiluːpadeɾeati0.265121
1949mətsajoməkʔəminememətpʔuɣərkiməkmʌtsaːomakʌmmiɲememapurtijmok0.201109
1820nəmŋəɬteɬqenwaŋqaremakenkuuweŋeaŋqaɬʔənammuːteːçmaɔnqareːmakənuːpkuːəŋəhaŋqalən0.298387
2855ilidūwďandukďapkundidodadko0.519713
86ăcyerqŋǣsa?tnθe0.680352
2681ŋə̄ləwsikōətnamatəamawunəwkīdōldīrəɲevibsikootamataapamaonotitoteiva0.277880
677Ŋanirmanda:airmanta0.275660
2787fśo1.000000
186Tyukoonaŋob'syudbya,kanmuːsali0.537903
2819hawali mhagdandulājīhɑːalhamdəndlaɪ0.333871
\n", "" ], "text/plain": [ " transcription \\\n", "2085 bəjunməńanətontukpəktirōrəpadrat \n", "1949 mətsajoməkʔəminememətpʔuɣərkimək \n", "1820 nəmŋəɬteɬqenwaŋqaremakenkuuweŋeaŋqaɬʔən \n", "2855 ilidūwďandukďapkun \n", "86 ăcyerqŋǣsa? \n", "2681 ŋə̄ləwsikōətnamatəamawunəwkīdōldīrə \n", "677 Ŋanirmanda: \n", "2787 fśo \n", "186 Tyukoonaŋob'syudbya, \n", "2819 hawali mhagdandulājī \n", "\n", " recognized phonetic_ev \n", "2085 bojuːmaɲanatontpuktiluːpadeɾeati 0.265121 \n", "1949 mʌtsaːomakʌmmiɲememapurtijmok 0.201109 \n", "1820 ammuːteːçmaɔnqareːmakənuːpkuːəŋəhaŋqalən 0.298387 \n", "2855 didodadko 0.519713 \n", "86 tnθe 0.680352 \n", "2681 ɲevibsikootamataapamaonotitoteiva 0.277880 \n", "677 airmanta 0.275660 \n", "2787 1.000000 \n", "186 kanmuːsali 0.537903 \n", "2819 hɑːalhamdəndlaɪ 0.333871 " ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[['transcription', 'recognized', 'phonetic_ev']].sample(10)" ] }, { "cell_type": "code", "execution_count": 43, "id": "928531c0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "df.phonetic_ev.plot.hist(bins=50)" ] }, { "cell_type": "code", "execution_count": null, "id": "da9546ac", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "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": "3.7.4" } }, "nbformat": 4, "nbformat_minor": 5 }