def listen(language):
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
p = pyaudio.PyAudio()
while GPIO.input(23)==False:
continue
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK) #buffer
print("* recording")
frames = []
while GPIO.input(23):
data = stream.read(CHUNK)
frames.append(data)
print("* done recording")
filename='output_'+str(int(time.time()))+'.wav'
stream.stop_stream()
stream.close()
p.terminate()
wf = wave.open(filename, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()
return stt.stt_google_wav(filename, language)
def listen(language):
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
p = pyaudio.PyAudio()
while GPIO.input(23) == False:
continue
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK) #buffer
print("* recording")
frames = []
while GPIO.input(23):
data = stream.read(CHUNK)
frames.append(data)
print("* done recording")
filename = 'output_' + str(int(time.time())) + '.wav'
stream.stop_stream()
stream.close()
p.terminate()
wf = wave.open(filename, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()
return stt.stt_google_wav(filename, language)
def passive_listen(language, threshold=THRESHOLD, num_phrases=-1):
"""
Listens to Microphone, extracts phrases from it and sends it to
s TTS service and returns response. a "phrase" is sound
surrounded by silence (according to threshold). num_phrases controls
how many phrases to process before finishing the listening process
(-1 for infinite).
"""
#Open stream
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK)
print "* Listening mic. "
audio2send = []
cur_data = '' # current chunk of audio data
rel = RATE / CHUNK
slid_win = deque(maxlen=SILENCE_LIMIT * rel)
#Prepend audio from 0.5 seconds before noise was detected
prev_audio = deque(maxlen=PREV_AUDIO * rel)
started = False
n = num_phrases
response = []
for i in range(0, RATE / CHUNK *
LISTEN_TIME): #Listen for the name just the time we decide
while (num_phrases == -1 or n > 0):
cur_data = stream.read(CHUNK)
slid_win.append(math.sqrt(abs(audioop.avg(cur_data, 4))))
#print slid_win[-1]
if (sum([x > THRESHOLD for x in slid_win]) > 0):
if (not started):
print "Starting record of phrase"
started = True
audio2send.append(cur_data)
elif (started is True):
print "Finished"
# The limit was reached, finish capture and deliver.
filename = save_speech(list(prev_audio) + audio2send, p)
# Send file to Google and get response
r = stt.stt_google_wav(filename, language)
if num_phrases == -1:
return r
else:
response.append(r)
# Remove temp file. Comment line to review.
os.remove(filename)
# Reset all
started = False
slid_win = deque(maxlen=SILENCE_LIMIT * rel)
prev_audio = deque(maxlen=0.5 * rel)
audio2send = []
n -= 1
print "Listening ..."
else:
prev_audio.append(cur_data)
print "* Done recording"
stream.close()
p.terminate()
return response
def passive_listen(language, threshold=THRESHOLD, num_phrases=-1):
"""
Listens to Microphone, extracts phrases from it and sends it to
s TTS service and returns response. a "phrase" is sound
surrounded by silence (according to threshold). num_phrases controls
how many phrases to process before finishing the listening process
(-1 for infinite).
"""
#Open stream
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK)
print "* Listening mic. "
audio2send = []
cur_data = '' # current chunk of audio data
rel = RATE/CHUNK
slid_win = deque(maxlen=SILENCE_LIMIT * rel)
#Prepend audio from 0.5 seconds before noise was detected
prev_audio = deque(maxlen=PREV_AUDIO * rel)
started = False
n = num_phrases
response = []
for i in range(0, RATE / CHUNK * LISTEN_TIME): #Listen for the name just the time we decide
while (num_phrases == -1 or n > 0):
cur_data = stream.read(CHUNK)
slid_win.append(math.sqrt(abs(audioop.avg(cur_data, 4))))
#print slid_win[-1]
if(sum([x > THRESHOLD for x in slid_win]) > 0):
if(not started):
print "Starting record of phrase"
started = True
audio2send.append(cur_data)
elif (started is True):
print "Finished"
# The limit was reached, finish capture and deliver.
filename = save_speech(list(prev_audio) + audio2send, p)
# Send file to Google and get response
r = stt.stt_google_wav(filename, language)
if num_phrases == -1:
return r
else:
response.append(r)
# Remove temp file. Comment line to review.
os.remove(filename)
# Reset all
started = False
slid_win = deque(maxlen=SILENCE_LIMIT * rel)
prev_audio = deque(maxlen=0.5 * rel)
audio2send = []
n -= 1
print "Listening ..."
else:
prev_audio.append(cur_data)
print "* Done recording"
stream.close()
p.terminate()
return response