My model doesn't recognite any word

Speech Recognition Toolkit

Brought to you by: air, arthchan2003, awb, bhiksha, and 5 others

This project can now be found here.

My model doesn't recognite any word

Forum: Help

Creator: Mariano Baci

Created: 2019-10-22

Updated: 2019-10-23

Mariano Baci - 2019-10-22

I'm creating a Speech recognition for my language for my very first time and to do it I follow a tutorial in youtube because I didn't understand the CMU Sphinx tutorial. I have done everything exactly like the tutorial and everything go exactly like the video but my model doesnt recognize any single word. Please help me. Thanks in advance.

feat.params

other.dic

other.filler

other.lm.DMP

other.phone

other_test.fileids

other_test.transcription

other_train.fileids

other_train.transcription

sphinx_train.cfg

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2019-10-22
  
  You need to share the whole model training folder, not just the model files.
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
  - Mariano Baci - 2019-10-22
    
    Very thanks for this email. I'm 10th year class student and an absolute
    beginner about the CMU Sphinx. I don't even know how to upload the whole
    training folder but I will try right now so please see it. Thanks again and
    so sorry for my English.
    
    alternate
    
    If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

How can I do this? When i select the folder it show just the open button.

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2019-10-22
  
  Share on google drive and post here a link.
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

Okay, just give me 1 second

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

https://drive.google.com/open?id=1Zshmt-7_O24v7rSFGVld16tPtGXou2Gz
Here is the full folder

Last edit: Mariano Baci 2019-10-22

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2019-10-22
  
  The link points to a file, not to a folder.
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

Please try again

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

Can you open the folder now? I changed the link.

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2019-10-22
  
  You do not have enough data for training. Our tutorial lists proper data requirements, you just need to read it. Remember - instagram and youtube makes it hard to you to comprehend information, reading big books is very important.
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

Can you please send me the link of the tutorial?

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Nickolay V. Shmyrev - 2019-10-22
  
  http://cmusphinx.github.io/wiki/tutorialam
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
  - Mariano Baci - 2019-10-22
    
    Thank you so much. I'm reading and I hope to understand it. But is there any folder of "perfect" example of training an acoustic model? I hope you will understand me.
    
    If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Nickolay V. Shmyrev - 2019-10-22

It is also listed in tutorial. Called "an4".

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
- Mariano Baci - 2019-10-22
  
  I download the an4 project and I watched it carefully but I didn't understand why in the wav folder is not any .wav file
  
  If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
  - Nickolay V. Shmyrev - 2019-10-22
    
    There are wav files, they just have different extension .sph.
    
    If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
    - Mariano Baci - 2019-10-23
      
      Oh okay, I converted them. Now I'm understanding more about CMU Shpinx. But is possible to create a language model for a new language with Kaldi? Because I have read that Kaldi is more accurate then CMU Sphinx.
      
      Last edit: Mariano Baci 2019-10-23
      
      If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

Thank you so much!!! You help me a lot. I was so confused. Thanks again!

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Mariano Baci - 2019-10-22

But why in the wav folder isn't any .wav audio file?

If you would like to refer to this comment somewhere else in this project, copy and paste the following link:

Log in to post a comment.