Comments (6)
Could you post one of the log files: exp/make_spec/make_fbank_pa_eval_spec.*.log
It is a common practice (in speech) to take the log-scale on the magnitude spectrogram.
from assert.
This is one of them, and thanks for your reply.
make_fbank_pa_eval_spec.1.log
from assert.
seems like there's something wrong with you wav.scp
ERROR (compute-spectrogram-feats[5.5.424~1-b5385]:Read():wave-reader.cc:122) WaveData: expected RIFF or RIFX, got fLaC
This is an example of my wav.scp and you can read more about data preparation for Kaldi.
LA_E_1003228-LA_E_1003228 sox /export/b14/jlai/ASVspoof2019-data/LA/ASVspoof2019_LA_eval/flac/LA_E_1003228.flac -r 16k -t wav -b 16 -e signed-integer - |
LA_E_1004363-LA_E_1004363 sox /export/b14/jlai/ASVspoof2019-data/LA/ASVspoof2019_LA_eval/flac/LA_E_1004363.flac -r 16k -t wav -b 16 -e signed-integer - |
LA_E_1005565-LA_E_1005565 sox /export/b14/jlai/ASVspoof2019-data/LA/ASVspoof2019_LA_eval/flac/LA_E_1005565.flac -r 16k -t wav -b 16 -e signed-integer - |
from assert.
It works, thx:)
from assert.
@Infinitestudy
I have successfully get the feature by run_feature.sh.But I dont know how to generate these files in main.py
data_files = { # training
'train_scp': 'data_reader/feats/la_train_spec_tensor4.scp',
'train_utt2index': 'data_reader/utt2systemID/la_train_utt2index_8',
'dev_scp': 'data_reader/feats/la_dev_spec_tensor4.scp',
'dev_utt2index': 'data_reader/utt2systemID/la_dev_utt2index_8',
'dev_utt2systemID': 'data_reader/utt2systemID/la_dev_utt2systemID',
'scoring_dir': 'scoring/la_cm_scores/',
}
from assert.
@wuqiangch are you able to generate the files above?
from assert.
Related Issues (20)
- How did you do system combination for your primary model? HOT 1
- It is easy to overfit HOT 1
- logspec feature extraction from run_features.sh HOT 1
- example of utt2systemID
- the missing bash script ‘make_spectrogram.sh’ HOT 16
- post() function for class analysis
- can you give me some guidance on how to use Bosaris toolkit HOT 1
- run_feature.sh: line 46: utils/copy_data_dir.sh: No such file or directory
- utt2systemID_file?
- Initialization has great impact on detection performance? HOT 1
- Parameters/Configurations of the pretrained models
- Docker availability?
- How to create .scp and utt2spk
- No such file or directory: u'data_reader/feats/la_dev_spec_tensor4.scp' HOT 1
- problem in main.py HOT 3
- the pretrained/pa/senet34 is binary_class? HOT 3
- How using python to get the logspec? HOT 1
- the problem of training model by SENet34 HOT 5
- focal_loss can help decrease the eer? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from assert.