Home › Forums › OpenEars › Mixing JSGF and default using changeLanguageModelToFile › Reply To: Mixing JSGF and default using changeLanguageModelToFile
I can confirm this doesn’t work for me.
I get a EXC_BAD_ACCESS at #0 0x00000001000f8d78 in fsg_lextree_init ()
…after I switch to a second JSGF model using the changeLanguageModelToFile API. (not during the call – which succeeds – but after I resume recognition.)
The models and their respective files were both successfully created. The first JSGF dynamic dictionary works fine.
This works great if I am using models created from Arrays.
Also – although I haven’t made it that far yet, I’m hoping I can switch between array and dictionary models dynamically so I can use a relatively large vocabulary (hundreds of words) for taking a note, but a small grammar (a dozen or less phrases) when navigating menus.
I’m hoping to avoid having to completely stop and start listening as it creates a number of performance, reliability and structural challenges.
Any advice?