Comments (6)
Hello,
Thank you. As you mentioned, the final.mdl is replicated from the GMM directory. The neural network dnn.nnet.h5 has no transition model, and so we need the final.mdl during decoding (transitions are not trained in this setup).
I'm haven't used nnet3, so I can't compare them. However, I guess nnet3 uses C++, so it should be faster than Python.
Regarding decoding on CPU vs GPU, I used small (3-hidden layer) models to test short utterances (less than five seconds). GPU actually took a little longer, perhaps for moving data in and out of its memory. If we tested larger models and longer utterances, the forward pass would be considerably faster on GPU. Training on GPU was surely several folds faster than on CPU.
To convert the models to nnet3, the DNN first needs to be converted into nnet3's raw format. Weights and biases of each DNN layer need to be printed from Python. The model can be loaded using load_model() method of keras.models. Each layer from the list layers of the model has a get_weights() method that retrieves the bias vector and the weight matrix as another list. After we get the DNN in raw format, we could feed nnet3-am-init with the available final.mdl and initialise with the trained weights and GMM's transition model.
Thanks,
Pavan.
from keras-kaldi.
thanks.
Never tempted to do a full DNN training from the filter banks features directly ?
from keras-kaldi.
I believe filterbanks perform similarly to MFCCs; they are just a linear transformation of untruncated MFCCs. I did test them sometime ago; I have no results currently.
from keras-kaldi.
oh yes I know, I meant without the GMM/HMM transition model. features directly feeding the network.
from keras-kaldi.
Like a sequence-to-sequence RNN? No I didn't, but it's definitely interesting to look at.
from keras-kaldi.
Yes that's what I have in mind but what I don't get is that most implementation for this are with a CTC loss function stuff. purely seq 2 seq does not seem to be easily doable.
from keras-kaldi.
Related Issues (15)
- getBinaryLabels function not defined HOT 1
- Can this code work on a tensorflow trained model HOT 6
- Phone error rates below ~50% HOT 2
- Any pretrained model available? HOT 2
- problem during runing run_kt.sh HOT 2
- Problem with 'dataGenSequences' object has no attribute shape HOT 3
- exp/tri2b Data Processing HOT 2
- ImportError HOT 2
- self.inputFeatDim in steps_kt/dataGenerator.py HOT 10
- samples_per_epoch in steps_kt/train.py HOT 2
- Data generator error when finishing epoch HOT 6
- Different form of input? HOT 3
- subprocess error HOT 2
- Training an cnn acoustic model with already trained model in keras HOT 22
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 keras-kaldi.