Add download script

download.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+mirror='https://ru-open-stt.ams3.digitaloceanspaces.com'
+
+while true; do
+	for file in $(cut -f2 -d' ' md5sum.lst); do
+		wget -c "${mirror}/${file}"
+	done
+
+	echo ''
+	echo '>>> Checking MD5 digests...'
+
+	md5sum -c md5sum.lst 1>md5sum.log 2>/dev/null
+	status=$?
+
+	if test $status -eq 0; then
+		rm md5sum.log
+		echo '>>> Data is downloaded and checked.'
+		break
+	fi
+
+	for failed in $(grep 'FAILED$' md5sum.log | grep -Po '^[^:]+'); do
+		echo ">>> MD5 digest for ${failed} is incorrect, the file will be downloaded again."
+		rm -f ${failed}
+	done
+
+	echo ''
+done

md5sum.lst

@@ -0,0 +1,37 @@
+b0ce7564ba90b121aeb13aada73a6e30 asr_public_phone_calls_1.csv
+6867d14dfdec1f9e9b8ca2f1de9ceda6 asr_public_phone_calls_2.csv
+0bdd77e15172e654d9a1999a86e92c7f asr_public_stories_1.csv
+f388013039d94dc36970547944db51c7 asr_public_stories_2.csv
+3b67e27c1429593cccbf7c516c4b582d private_buriy_audiobooks_2.csv
+04027c20eb3aff05f6067957ecff856b public_lecture_1.csv
+89da3f1b6afcd4d4936662ceabf3033e public_series_1.csv
+a81dfb018c88d0ecd5194ab3d8ff6c95 public_youtube700.csv
+c858f020729c34ba0ab525bbb8950d0c ru_RU.csv
+0275525914825dec663fd53390fdc9a0 russian_single.csv
+52f406f4e30fcc8c634f992befd91beb tts_russian_addresses_rhvoice_4voices.csv
+a5496898ee78654bf398ec6df71540d7 asr_public_phone_calls_1.tar.gz
+97594127a922df8a7bcc2eecd2470805 asr_public_phone_calls_2.tar.gz_aa
+f9b6475f0f2898b16d9e6e0e648fb531 asr_public_phone_calls_2.tar.gz_ab
+b19977c889cda639f621195251e6bb6f asr_public_phone_calls_2.tar.gz_ac
+657a31b544b10295f909ef4b2ca5c156 asr_public_stories_1.tar.gz
+7533581bb26975212817bcacb25546d0 asr_public_stories_2.tar.gz
+3955616cd89761bf2d54d0e992f7eae5 audiobooks_2.tar.gz_aa
+81b6ec147c0c43bdd56002c41e0288b8 audiobooks_2.tar.gz_ab
+15d4cf99171c2db3f375619f4bd2b6d9 audiobooks_2.tar.gz_ac
+50635b0f4bdf44fae96e5a65f4738e19 audiobooks_2.tar.gz_ad
+f1103be39ffc2da4a98d8f6ddeb50aa0 audiobooks_2.tar.gz_ae
+8b45d2bd8b1fa1d906e36b9fabd9fe4c audiobooks_2.tar.gz_af
+5104df44933b612b3c1bfc06f6376654 audiobooks_2.tar.gz_ag
+e6b9e5f46811d33ea34ce50f6067a762 public_lecture_1.tar.gz
+86ebf7e30986b8ee8df11f85b35588a0 public_series_1.tar.gz
+dc260dd8151b4fce6cde6d80af13146d public_youtube700.tar.gz_aa
+04706ef0f98841ec8d2f20a83aca3cf1 public_youtube700.tar.gz_ab
+e11d5b118bf71425e4915e61277a06a9 public_youtube700.tar.gz_ac
+d9a93157263eb9d8078c0e0b88c271de public_youtube700.tar.gz_ad
+1bbba5eb2f4911c9ed20ec69cbd292cb ru_ru.tar.gz
+6f79a9c514ad48a5763e3142919fc765 russian_single.tar.gz
+31d515e0bdfc467c3fe63088b817c15c tts_russian_addresses_rhvoice_4voices.tar.gz_aa
+4ca15694a8d8a638bbdc5e90832eadb4 tts_russian_addresses_rhvoice_4voices.tar.gz_ab
+447559a38cd8bf61c5de64e602f06da3 tts_russian_addresses_rhvoice_4voices.tar.gz_ac
+9131347a97c2e794d7c6d5a265083e83 tts_russian_addresses_rhvoice_4voices.tar.gz_ad
+91e2115b17b1ad08649f428d2caa643b voxforge_ru.tar.gz