Pregunta

I've learned the basics of how to use Shpinx-4 as a speech recognition Toolkit.

I've wrote number of sentences to build the language model for my small project(As a start 10 sentences) to train since the performance of the SR was not very good for my question.

Then I did upload it to: http://www.speech.cs.cmu.edu/tools/lmtool-new.html

I mainly read this http://cmusphinx.sourceforge.net/wiki/tutoriallm to learn how to create a language model.

  • Now, What shall I do next to use it?
  • and can I still use the en-us.lm.dmp language model?

Many Thanks

¿Fue útil?

Solución

Now, What shall I do next to use it?

You can specify it in your source code a for tutorial as

configuration.setLanguageModelPath("file:<path_to_your_new_model>");

In that case your new language model will be loaded and used for recognition

and can I still use the en-us.lm.dmp language model?

You can switch between them in runtime.

Licenciado bajo: CC-BY-SA con atribución
No afiliado a StackOverflow
scroll top