pocketsphinx setting mandarin model and dictionary problem

[Cindy Chang]

I copy the demoapp.py from the offical website, then I do some alteration.
My language model is downloaded from here: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/Mandarin/zh_broadcastnews_64000_utf8.DMP/download
Here is my init_gst( I only modify this function)

    def init_gst(self):
        """Initialize the speech components"""

        self.pipeline = gst.parse_launch('autoaudiosrc ! audioconvert !  audioresample '
                                         + '! pocketsphinx name=asr ! fakesink')

        bus = self.pipeline.get_bus()
        bus.add_signal_watch()
        bus.connect('message::element', self.element_message)

        self.pipeline.set_state(gst.State.PAUSED)
        asr = self.pipeline.get_by_name('asr');  # We previously  assigned pocketsphinx element a name asr
        asr.set_property('lm', '/Users/cindy/Documents/pythonworkspace/sphinxenv/chinese.lm')
        asr.set_property('dict', '/Users/cindy/Documents/pythonworkspace/sphinxenv/dict/chinese_dict.dict')

and here is the dict file:

前進 t ing zh ib
後退 h ou t ui
左轉 z uo zh uan
右轉 y uo zh uan
向左轉 x iang z uo zh uan
向右轉 x iang y uo zh uan
停止 t ing zh ib
加速 j ia s u
減速 j ian s u

However, when I click the button speak and say some chinese words,
nothing appear in the textbox.

Please help.

[Kevin Lenzo]

The models on VoxForge have 192 phonemes in them, which is more than the usual maximum of 128. To make this work with 192, you will need to edit

pocketsphinx/src/libpocketsphinx/fsg_lextree.h

at about line 65. Change

#define FSG_PNODE_CTXT_BVSZ 4

to

#define FSG_PNODE_CTXT_BVSZ 6

and re-compile.

[Kevin Lenzo]

[Kevin Lenzo]

[Cindy Chang]

Since there is no any error message showing, I need some code or command to help me print some debug information.

[Lisa Loo]

i have the same issue can advise?

[Kevin Lenzo]

Answered above