After some trying to make CMUsphinx work with Persian language, I thought it's better and easier to use Google speech API. but I think it's cloud base and can't work offline! So I am thinking if we could use the google's resources like dictionary or acoustic model it would be very good! but I don't know is it possible?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Its the same problem for Arabic language. In my case, I don't find an acoustic model and language model to work with. When I tried google speech API , i got a better result. The Google API resulted by recognizing almost pronunciated words. If google share her models, we can work with to deploy any app that needs a large vocabulary. I'm excited to know if its possible!!.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
After some trying to make CMUsphinx work with Persian language, I thought it's better and easier to use Google speech API. but I think it's cloud base and can't work offline! So I am thinking if we could use the google's resources like dictionary or acoustic model it would be very good! but I don't know is it possible?
Its the same problem for Arabic language. In my case, I don't find an acoustic model and language model to work with. When I tried google speech API , i got a better result. The Google API resulted by recognizing almost pronunciated words. If google share her models, we can work with to deploy any app that needs a large vocabulary. I'm excited to know if its possible!!.
Eqra tech has Arabic model you can contact them on info at reqratech dot
com
Last edit: hiyassat 2017-09-24
Thank you so much hiyassat.
I didn't find any Arabic model to practice with. Any help is better appreciated.
Thanks for any Help.