qiny1012 / kaldi_x-vector_aishell Goto Github PK
View Code? Open in Web Editor NEWUsing Kaldi x-vector method to train speaker recognition model on aishell database.
Using Kaldi x-vector method to train speaker recognition model on aishell database.
楼主您好,我想请教一下有关训练的问题,我是第一部分出现了错误,在跑new_01的时候,出现了这个错误:Error: local/aishell_data_prep.sh requires two directory arguments 我看了aishell_data_prep.sh里面应该是在26 27行那里。path.sh里面的路径已经更改了,我是初学kaldi,不太清楚这个error的原因,所以想请教你一下。如果能方便交流的话,能加您QQ是最好了,我的q是546866700,谢谢您了
大佬,在第六步,为什么你的Iter: x/719 。我的只有Iter: x/159哈,num-epochs都是80,其它参数也一样,上一步得到的句子数量都一样
fix_data_dir.sh: kept all 600490 utterances.
fix_data_dir.sh: old files are kept in data/train_combined_no_sil/.backup
fix_data_dir.sh: kept all 590655 utterances.
fix_data_dir.sh: old files are kept in data/train_combined_no_sil/.backup
所以我最终的结果很差:
EER: 3.387%
minDCF(p-target=0.01): 0.3582
minDCF(p-target=0.001): 0.5667
是我哪里参数有问题吗,或者说Iter的参数在哪里调?
想问一下楼主,怎么看训练的x-vector维度是多少啊?
楼主你好,我在new_04的时候出现了以下问题:
steps/make_mfcc.sh --mfcc-config conf/mfcc.conf --nj 20 --cmd utils/parallel/run.pl --mem 10G data/train_aug exp/make_mfcc feature/mfcc
utils/validate_data_dir.sh: Successfully validated data-directory data/train_aug
steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.
steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (360294 != 480392); consider using utils/fix_data_dir.sh data/train_aug
steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error.
是因为前面数据增强准备的数据有问题么?用的是和您一样的数据集。
我在new_01脚本执行,进入到aishell_data_prep.sh的32行时就会exit 1:
line 32:find $aishell_audio_dir -iname "*.wav" | grep -i "wav/train" > $train_dir/wav.flist || exit 1;
是不是我数据集准备的格式有点问题,如果觉得在这个上面交流不便我的qq是2357861275,可以备注git,我想多多请教一下您,因为我是初学kaldi,谢谢您了
作者你好,在执行new_02时,出现了usage: run.pl log-file command-line arguments... at utils/parallel/run.pl line 26.这一问题,求助怎么解决
给ipynb文件点赞!
大佬,想问下就这个代码想提升识别结果的话有什么方法吗?我想到的是:1、提高mfcc维度,用40维,2、训练TDNN更多轮,训1000轮吧,3,用aishell2的数据集替代aishell1?请问这几个方法可行吗
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.