diff options
| -rwxr-xr-x | Blather.py | 5 | ||||
| -rw-r--r-- | README | 25 | ||||
| -rwxr-xr-x | Recognizer.py | 15 |
3 files changed, 31 insertions, 14 deletions
diff --git a/Blather.py b/Blather.py index f5d8a67..6ec6b02 100755 --- a/Blather.py +++ b/Blather.py @@ -34,7 +34,7 @@ class Blather: self.continuous_listen = False self.commands = {} self.read_commands() - self.recognizer = Recognizer(lang_file, dic_file) + self.recognizer = Recognizer(lang_file, dic_file, opts.microphone ) self.recognizer.connect('finished',self.recognizer_finished) if opts.interface != None: @@ -155,6 +155,9 @@ if __name__ == "__main__": parser.add_option("-H", "--history", type="int", action="store", dest="history", help="number of commands to store in history file") + parser.add_option("-m", "--microphone", type="int", + action="store", dest="microphone", default=None, + help="Audio input card to use (if other than system default)") (options, args) = parser.parse_args() #make our blather object diff --git a/README b/README index a4a47d7..b88048d 100644 --- a/README +++ b/README @@ -1,9 +1,9 @@ #Blather -Blather is a speech recognizer that will run commands when a user speaks preset sentences. +Blather is a speech recognizer that will run commands when a user speaks preset sentences. ##Requirements -1. pocketsphinx -2. gstreamer (and what ever plugin has pocket sphinx support) +1. pocketsphinx +2. gstreamer (and what ever plugin has pocket sphinx support) 3. pyside (only required for the Qt based UI) 4. pygtk (only required for the Gtk based UI) @@ -17,13 +17,22 @@ Blather is a speech recognizer that will run commands when a user speaks preset 6. run Blather.py * for Qt GUI, run Blather.py -i q * for Gtk GUI, run Blather.py -i g - * to start a UI in 'continuous' listen mode, use the -c flag - + * to start a UI in 'continuous' listen mode, use the -c flag + * to use a microphone other than the system default, use the -d flag 7. start talking ####Bonus once the sentences.corpus file has been created, run the language_updater.sh script to automate the process of creating and downloading language files. -**Example** -To run blather with the GTK UI and start in continuous listen mode: -./Blather.py -i g -c \ No newline at end of file +####Examples +To run blather with the GTK UI and start in continuous listen mode: +./Blather.py -i g -c + +To run blather with no UI and using a USB microphone recognized and device 2: +./Blather.py -d 2 + +####Finding the Device Number of a USB microphone +There are a few ways to find the device number of a USB microphone. + +* `cat /proc/asound/cards` +* `arecord -l` \ No newline at end of file diff --git a/Recognizer.py b/Recognizer.py index 8497839..26ccd80 100755 --- a/Recognizer.py +++ b/Recognizer.py @@ -16,11 +16,16 @@ class Recognizer(gobject.GObject): __gsignals__ = { 'finished' : (gobject.SIGNAL_RUN_LAST, gobject.TYPE_NONE, (gobject.TYPE_STRING,)) } - def __init__(self, language_file, dictionary_file): + def __init__(self, language_file, dictionary_file, src = None): gobject.GObject.__init__(self) self.commands = {} + if src: + audio_src = 'alsasrc device="hw:%d,0"' % (src) + else: + audio_src = 'autoaudiosrc' + #build the pipeline - cmd = 'autoaudiosrc ! audioconvert ! audioresample ! vader name=vad ! pocketsphinx name=asr ! appsink sync=false' + cmd = audio_src+' ! audioconvert ! audioresample ! vader name=vad ! pocketsphinx name=asr ! appsink sync=false' self.pipeline=gst.parse_launch( cmd ) #get the Auto Speech Recognition piece asr=self.pipeline.get_by_name('asr') @@ -31,10 +36,10 @@ class Recognizer(gobject.GObject): #get the Voice Activity DEtectoR self.vad = self.pipeline.get_by_name('vad') self.vad.set_property('auto-threshold',True) - + def listen(self): self.pipeline.set_state(gst.STATE_PLAYING) - + def pause(self): self.vad.set_property('silent', True) self.pipeline.set_state(gst.STATE_PAUSED) @@ -42,4 +47,4 @@ class Recognizer(gobject.GObject): def result(self, asr, text, uttid): #emit finished self.emit("finished", text) - + |