def move_front(self):
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.move_forward()
else:
print("sorry! you don't have pi")
def turn_on_flash(self):
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.flash_white()
else:
print("sorry! you don't have pi")
def __enter__(self):
p = pyaudio.PyAudio()
info = p.get_host_api_info_by_index(0)
numdevices = info.get('deviceCount')
for i in range(0, numdevices):
if (p.get_device_info_by_host_api_device_index(
0, i).get('maxInputChannels')) > 0:
print(
"Input Device id ", i, " - ",
p.get_device_info_by_host_api_device_index(0,
i).get('name'))
self._audio_interface = pyaudio.PyAudio()
self._audio_stream = self._audio_interface.open(
format=pyaudio.paInt16,
# The API currently only supports 1-channel (mono) audio
# https://goo.gl/z757pE
channels=1,
rate=self._rate,
input=True,
frames_per_buffer=self._chunk,
# Run the audio stream asynchronously to fill the buffer object.
# This is necessary so that the input device's buffer doesn't
# overflow while the calling thread makes network requests, etc.
stream_callback=self._fill_buffer,
input_device_index=get_env_value('AUDIO_DEVICE_INDEX2'))
self.closed = False
return self
def listen_speech(self):
# obtain audio from the microphone
for index, name in enumerate(sr.Microphone.list_microphone_names()):
print("Microphone with name \"{1}\" found for `Microphone(device_index={0})`".format(index, name))
# obtain audio from the microphone
r = sr.Recognizer()
try:
with sr.Microphone(device_index=get_env_value('AUDIO_DEVICE_INDEX1')) as source:
r.adjust_for_ambient_noise(source, duration=1)
print("Say something!")
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.flash_red()
else:
print("sorry! can't blink red you don't have pi")
audio = r.listen(source,phrase_time_limit=2)
except Exception as e:
print(e)
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.flash_yellow()
else:
print("sorry! can't blink yellow you don't have pi")
print("converting")
# recognize speech using Google Speech Recognition
try:
# for testing purposes, we're just using the default API key
# to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
# instead of `r.recognize_google(audio)`
text = r.recognize_google(audio)
print("Speech Recognition thinks you said " + text)
self.ai.get_reply_as_speech(text)
except sr.UnknownValueError:
print("Speech Recognition could not understand audio")
except sr.RequestError as e:
print("Could not request results from Speech Recognition service; {0}".format(e))
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.flash_blue()
else:
print("sorry! can't blink blue you don't have pi")
def __del__(self):
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.no_led_flash()
else:
print("sorry! can't blink yellow you don't have pi")
print(PrintColors.WARNING + "killing ngrok")
self.process.kill()
def __start_avconv(self):
stream_url = self.__get_stream_url()
LiveStream.process = subprocess.Popen([
'avconv', '-f', 'video4linux2', '-r', '10', '-i', '/dev/video0',
'-f', 'pulse', '-ac', '1', '-i',
get_env_value('AUDIO_DEVICE'), '-vcodec', 'h264', '-preset',
'medium', '-acodec', 'mp3', '-ar', '44100', '-threads', '1',
'-qscale', '3', '-b:a', '128k', '-b:v', '500k', '-minrate', '500k',
'-g', '60', '-pix_fmt', 'yuv420p', '-f', 'flv', stream_url
],
stdout=subprocess.PIPE)
def stream_speach(self):
try:
if get_env_value('DEVICE') == 'PI':
from lib.PiControls import PiControls
pi = PiControls()
pi.flash_blue()
else:
print("sorry! can't blink blue you don't have pi")
print('live speech recognition started')
print(threading.enumerate())
# See http://g.co/cloud/speech/docs/languages
# for a list of supported languages..
language_code = 'en-US' # a BCP-47 language tag
credentials = service_account.Credentials.from_service_account_file(
'google-cloud.json')
client = speech.SpeechClient(credentials=credentials)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=RATE,
language_code=language_code)
streaming_config = types.StreamingRecognitionConfig(
config=config,
interim_results=True)
with MicrophoneStream(RATE, CHUNK) as stream:
audio_generator = stream.generator()
requests = (types.StreamingRecognizeRequest(audio_content=content)
for content in audio_generator)
responses = client.streaming_recognize(streaming_config, requests)
# Now, put the transcription responses to use.
self.listen_print_loop(responses)
except:
print('exception occured')
self.stream_speach()