Comments (16)
Hi, i checked the thchs30 Kaldi recipe and saw that the decoding is based on the standard steps/decode.sh of kaldi. Therefore, it should work with our toolkit. When running the standard kaldi recipe, do you obtain the WER / PER at the end of decoding ? If so, the decoder is able to find the stm and glm files that should exist somewhere ?
from pytorch-kaldi.
Ok, so the scoring part of the thchs30 is custom. check at local/score.sh in the Kaldi recipe. You might need to call this script to score instead of our.
from pytorch-kaldi.
I am very glad that you can reply so quickly.Do I need to change the score.sh in your demo follow local/score.sh? Can you give me some tips about this?
from pytorch-kaldi.
Exactly, you have to replace this call to the right score.sh file.
from pytorch-kaldi.
thank you,i will try to do it.
from pytorch-kaldi.
Hi, I have the same problem while decoding and scoring the test dataset. My kaldi part of the experiment only generates alignment and graphs. The data preparation I performed does not create stm and glm files. I am using TIMIT_MLP_basic as configuration file. If I create stm and glm file only for the test dataset and store in the test data directory, will the problem be solved or there are other files needed to be created?
from pytorch-kaldi.
What is your dataset ?
from pytorch-kaldi.
from pytorch-kaldi.
In order to solve this problem, I just changed the default script of decode to the custom decode script provided in thchs30.
But I think it won't solve your problem.
from pytorch-kaldi.
I created my own stm and glm files for my test dataset (using TIMIT as reference) then I used TIMIT_MLP_basic configuration as it is. It worked. Thanks
from pytorch-kaldi.
OK
from pytorch-kaldi.
from pytorch-kaldi.
from pytorch-kaldi.
from pytorch-kaldi.
Hi !
In general, for questions related to Kaldi, you better go into the official google-group, you will obtain more detailed and precise answers.
-
First, MLP is a bad solution to get good PER. How is the loss evolving during the training? Then, how much hours do you have ? Are the data clean or very noisy ? A lot of stuffs impacts the decoding. You should try with a bigger net to see first. IVectors, or speaker adaptation will help you to further reduce the PER, but when you're at 60% of PER, the solution is not a simple tweak, you must investigate other configurations and maybe features extraction.
-
It will be very very hard to computer Fmllr with other toolkits and connect to Kaldi, you should try to solve your problem with generating with Kaldi.
-
It should only be scoring test. The % reported for train and dev are within the training of the PyTorch acoustic model. Consequently, it's the loss function and not the PER. Unless you forced it ?
from pytorch-kaldi.
from pytorch-kaldi.
Related Issues (20)
- How to setup parameters in "cfg/TIMIT_baselines/TIMIT_liGRU_fmllr.cfg"? HOT 1
- Do bidirectional layers share the input-to-hidden weights? HOT 2
- Can we resume training from the epoch we got interruption HOT 4
- input shape of nns HOT 3
- Question about the Dimension of wx.0.weight in my mlp model HOT 1
- The loss curve of train and dev is reasonable but why the Test Error keeps 53% or so? HOT 8
- Support for torch.nn.Transformer Class? HOT 1
- KaldiFatalError during decoding phase
- No WER stdout when decoding
- Does pytorch-kaldi support chain model training? HOT 1
- Word transcription of TIMIT dataset HOT 1
- No Decoding Output HOT 20
- How to train/decode on reverberant speech? HOT 1
- x-vector DNN model
- Unable to run forwarding step on test set
- Before switch to SpeechBrain, how to use trained model in pytorch
- Use final_architecture1.pkl for live test HOT 4
- err_te is 1
- using different features instead of FMLLR
- res.res
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 pytorch-kaldi.