http://openslr.org/ OpenSLR is a site devoted to hosting speech and language resources, such as training corpora for speech recognition, and software related to speech recognition.
https://aishelltech.com/kysjcp aishell1数据下载 nohup wget https://openslr.elda.org/resources/33/data_aishell.tgz --no-check-certificate & wget https://openslr.elda.org/resources/33/resource_aishell.tgz ssh xt@101.43.140.244:/opt/soft ssh -p 26225 144.34.185.72 rsync -e 'ssh -p26225' -avP 144.34.185.72:/opt/soft/* ./
|
(base) xt@ai:~/data/data_aishell$ ll
total 28
drwxr-xr-x 4 xt xt 4096 6月 16 2017 ./
drwxrwxr-x 3 xt xt 4096 4月 12 16:15 ../
drwxr-xr-x 2 xt xt 4096 7月 5 2017 transcript/
drwxr-xr-x 2 xt xt 16384 6月 16 2017 wav/
transcript
(base) xt@ai:~/data/data_aishell$ ll transcript/
total 9864
drwxr-xr-x 2 xt xt 4096 7月 5 2017 ./
drwxr-xr-x 4 xt xt 4096 6月 16 2017 ../
-rw-r--r-- 1 xt xt 10091431 7月 5 2017 aishell_transcript_v0.8.txt
(base) xt@ai:~/data/data_aishell$ tail -f -n 3 transcript/aishell_transcript_v0.8.txt
BAC009S0916W0493 公司 却 遇到 了 资金 困难
BAC009S0916W0494 存在 无法 如期 还贷 的 风险
BAC009S0916W0495 这 令 被 贷款 的 员工 们 寝食 难 安
wav
$ ls wav/
S0002.tar.gz S0042.tar.gz S0082.tar.gz
(base) xt@ai:~/data/data_aishell$ ls wav/ | wc -l
400
(base) xt@ai:~/data/data_aishell$ cp wav/S0002.tar.gz /tmp/
(base) xt@ai:~/data/data_aishell$
(base) xt@ai:~/data/data_aishell$ cd /tmp/
(base) xt@ai:/tmp$ tar -xvf S0002.tar.gz
train/S0002/
train/S0002/BAC009S0002W0122.wav
train/S0002/BAC009S0002W0123.wav
train/S0002/BAC009S0002W0124.wav
train/S0002/BAC009S0002W0125.wav
train/S0002/BAC009S0002W0126.wav
...
...
(base) xt@ai:/tmp/train$ ls /tmp/train/S0002/ |wc -l
365
(base) xt@ai:~/data/data_aishell/wav$ cp S0916.tar.gz /tmp/data/
(base) xt@ai:~/data/data_aishell/wav$ cd /tmp/data/
(base) xt@ai:/tmp/data$ ls
S0916.tar.gz
(base) xt@ai:/tmp/data$ tar -xvf S0916.tar.gz
test/S0916/
test/S0916/BAC009S0916W0121.wav
test/S0916/BAC009S0916W0122.wav
(base) xt@ai:/tmp/data/test/S0916$ ls /tmp/data/test/S0916/|wc -l
361
|
|
vim get_data.sh
#!/bin/bash
# 遍历data目录下的所有.tar.gz文件
for file in /home/xt/data/data_aishell/wav/*.tar.gz; do
# 检查文件是否存在
if [ -f "$file" ]; then
# 解压文件
tar -xvf $file
else
echo "File does not exist: $file"
fi
done
[root@ki wav]# ls dev/
S0724 S0726 S0728 S0730 S0732 S0734 S0736 S0738 S0740 S0742 S0744 S0746 S0748 S0750 S0752 S0754 S0756 S0758 S0760 S0762
S0725 S0727 S0729 S0731 S0733 S0735 S0737 S0739 S0741 S0743 S0745 S0747 S0749 S0751 S0753 S0755 S0757 S0759 S0761 S0763
[root@ki wav]# ls test/
S0764 S0765 S0766 S0767 S0768 S0769 S0770 S0901 S0902 S0903 S0904 S0905 S0906 S0907 S0908 S0912 S0913 S0914 S0915 S0916
[root@ki wav]# ls train/
S0002 S0014 S0026 S0038 S0050 S0062 S0074 S0086 S0098 S0110 S0122 S0134 S0146 S0158 S0170 S0182 S0194 S0206 S0218 S0230 S0242 S0335 S0347 S0359 S0513 S0597 S0662 S0708 S0720
S0003 S0015 S0027 S0039 S0051 S0063 S0075 S0087 S0099 S0111 S0123 S0135 S0147 S0159 S0171 S0183 S0195 S0207 S0219 S0231 S0243 S0336 S0348 S0360 S0514 S0598 S0663 S0709 S0721
S0004 S0016 S0028 S0040 S0052 S0064 S0076 S0088 S0100 S0112 S0124 S0136 S0148 S0160 S0172 S0184 S0196 S0208 S0220 S0232 S0244 S0337 S0349 S0361 S0515 S0599 S0664 S0710 S0722
S0005 S0017 S0029 S0041 S0053 S0065 S0077 S0089 S0101 S0113 S0125 S0137 S0149 S0161 S0173 S0185 S0197 S0209 S0221 S0233 S0245 S0338 S0350 S0362 S0516 S0600 S0665 S0711 S0723
S0006 S0018 S0030 S0042 S0054 S0066 S0078 S0090 S0102 S0114 S0126 S0138 S0150 S0162 S0174 S0186 S0198 S0210 S0222 S0234 S0246 S0339 S0351 S0363 S0517 S0601 S0666 S0712
S0007 S0019 S0031 S0043 S0055 S0067 S0079 S0091 S0103 S0115 S0127 S0139 S0151 S0163 S0175 S0187 S0199 S0211 S0223 S0235 S0247 S0340 S0352 S0421 S0518 S0655 S0701 S0713
S0008 S0020 S0032 S0044 S0056 S0068 S0080 S0092 S0104 S0116 S0128 S0140 S0152 S0164 S0176 S0188 S0200 S0212 S0224 S0236 S0248 S0341 S0353 S0422 S0519 S0656 S0702 S0714
S0009 S0021 S0033 S0045 S0057 S0069 S0081 S0093 S0105 S0117 S0129 S0141 S0153 S0165 S0177 S0189 S0201 S0213 S0225 S0237 S0249 S0342 S0354 S0423 S0520 S0657 S0703 S0715
S0010 S0022 S0034 S0046 S0058 S0070 S0082 S0094 S0106 S0118 S0130 S0142 S0154 S0166 S0178 S0190 S0202 S0214 S0226 S0238 S0250 S0343 S0355 S0509 S0521 S0658 S0704 S0716
S0011 S0023 S0035 S0047 S0059 S0071 S0083 S0095 S0107 S0119 S0131 S0143 S0155 S0167 S0179 S0191 S0203 S0215 S0227 S0239 S0251 S0344 S0356 S0510 S0522 S0659 S0705 S0717
S0012 S0024 S0036 S0048 S0060 S0072 S0084 S0096 S0108 S0120 S0132 S0144 S0156 S0168 S0180 S0192 S0204 S0216 S0228 S0240 S0252 S0345 S0357 S0511 S0523 S0660 S0706 S0718
S0013 S0025 S0037 S0049 S0061 S0073 S0085 S0097 S0109 S0121 S0133 S0145 S0157 S0169 S0181 S0193 S0205 S0217 S0229 S0241 S0334 S0346 S0358 S0512 S0596 S0661 S0707 S0719
[root@ki wav]# pwd
/data/wave/aishell/data_aishell/wav
|
|
|
|
|
https://www.openslr.org/resources/18/data_thchs30.tgz https://www.openslr.org/resources/18/test-noise.tgz https://www.openslr.org/resources/18/resource.tgz
CONTACTOR
CONTACTOR
Dong Wang wangdong99@mails.tsinghua.edu.cn
Xuewei Zhang zxw@cslt.riit.tsinghua.edu.cn
Zhiyong Zhang zhangzy@cslt.riit.tsinghua.edu.cn
ROOM1-303, BLDG FIT
CSLT, Tsinghua University
http://cslt.org
http://cslt.riit.tsinghua.edu.cn
External URLs:
http://data.cslt.org/thchs30/README.html (Original URL from CSLT )
http://pan.baidu.com/s/1hqKwE00 ( Baidu disk )
xt@ai:/data/wave/data_thchs30$ ll
total 8261428
drwxrwxr-x 3 xt xt 4096 4月 5 19:22 ./
drwxr-xr-x 4 xt xt 4096 4月 5 18:27 ../
drwxr-xr-x 8 xt xt 4096 12月 30 2015 data_thchs30/
-rw-rw-r-- 1 xt xt 6453425169 10月 4 2017 data_thchs30.tgz
-rw------- 1 xt xt 9972323 1月 6 16:27 nohup.out
-rw-rw-r-- 1 xt xt 24813708 10月 4 2017 resource.tgz
-rw-rw-r-- 1 xt xt 1971460210 10月 4 2017 test-noise.tgz
xt@ai:/data/wave/data_thchs30$ cd data_thchs30/
xt@ai:/data/wave/data_thchs30/data_thchs30$ ls
data dev lm_phone lm_word README.TXT test train
/media/xt/DE22538E22536A93/data/yuyin/hanyu2/wav48 -rwxrwxrwx 1 1000 1000 81 Jan 25 2022 96 -rwxrwxrwx 1 1000 1000 566862 Jan 25 2022 96.wav -rwxrwxrwx 1 1000 1000 91 Jan 25 2022 97 -rwxrwxrwx 1 1000 1000 698958 Jan 25 2022 97.wav -rwxrwxrwx 1 1000 1000 53 Jan 25 2022 98 -rwxrwxrwx 1 1000 1000 569550 Jan 25 2022 98.wav -rwxrwxrwx 1 1000 1000 68 Jan 25 2022 99 -rwxrwxrwx 1 1000 1000 481230 Jan 25 2022 99.wav [root@ki wav48]# |
|
|
|
|
|
|
|