speech converstions on live audio stream

[raady07]

I want to throw the speech to text conversions on my console when the user has stopped speaking. For it I installed speech_recognition module and python2.

When I run on command line

python -m speech_recognition

it is able to detect the end of the user speech, convert it and print it on my console and returning back to listen the audio from mic until I stop it. I am not sure which converter it is using. The output is accurate enough

Output:
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
JackShmReadWritePtr::~JackShmReadWritePtr - Init not done for 4294967295, skipping unlock
JackShmReadWritePtr::~JackShmReadWritePtr - Init not done for 4294967295, skipping unlock
A moment of silence, please...
Set minimum energy threshold to 1806.92166802
Say something!
Got it! Now to recognize it...
I am testing this speech converters. I am done !
Say something!
Got it! Now to recognize it...
The second tw test going on. 

Now I am trying to do speech recognition through controlled way, using the code snippets examples given and I have choosen microsoft bing for converstions.

def convert_speech_to_text(audio):
	
	message = sr.Recognizer().recognize_bing(audio, key=BING_KEY)
	return(message)

while True:
    # try: 
	with sr.Microphone() as source:
		sr.Recognizer().adjust_for_ambient_noise(source)
		print(1,'say')
		audio = sr.Recognizer().listen(source)
		
	print("Converting")
	message = convert_speech_to_text(audio)
	print(message)
    # except: 
       # print("error")

my program works fine with out while loop, but when using it, it is stuck by printing (1,'say') and it is continuosly listening to the mic and not converting.

Is there any way I can reproduce the command

python -m speech_recognition

does as .py file?

[buran]

probably you can try

with sr.Microphone() as source:
    sr.Recognizer().adjust_for_ambient_noise(source)
    print(1,'say')
    while True:
        audio = sr.Recognizer().listen(source)
        print("Converting")
        message = convert_speech_to_text(audio)
        print(message)