def transcribe_audio(path_to_audio_file):
username = os.environ.get("STT_USERNAME")
password = os.environ.get("STT_PASSWORD")
speech_to_text = SpeechToText(username=username,
password=password)
with open(join(dirname(__file__), path_to_audio_file), 'rb') as audio_file:
return speech_to_text.recognize(audio_file,
content_type='audio/wav')
def transcribe_audio(self, path_to_audio_file):
#username = os.environ.get("BLUEMIX_USERNAME")
#password = os.environ.get("BLUEMIX_PASSWORD")
username = "******"
password = "******"
speech_to_text = SpeechToText(username=username, password=password)
with open(path_to_audio_file, 'rb') as audio_file:
return speech_to_text.recognize(audio_file,
content_type='audio/wav')
def main():
dotenv_path = join(dirname(__file__), '.env')
load_dotenv(dotenv_path)
stt = SpeechToText(username=os.environ.get("STT_USERNAME"),
password=os.environ.get("STT_PASSWORD"))
recorder = Recorder("speech.wav")
print("Please say something into the microphone\n")
recorder.record_to_file()
print("Transcribing audio....\n")
result = transcribe_audio(stt, 'speech.wav')
text = result['results'][0]['alternatives'][0]['transcript']
print("Text: " + text + "\n")
def speech_to_text(self, wavpath):
username = self.speechcreds['username']
password = self.speechcreds['password']
speech_to_text = SpeechToText(username=username,
password=password)
result = ""
fname = wavpath
try:
with open(fname, 'rb') as audio_file:
result = speech_to_text.recognize(audio_file,
content_type='audio/wav')
text = result['results'][0]['alternatives'][0]['transcript']
return text
except:
return "Something went wrong. Please try again."
import json
from os.path import join, dirname
from watson_developer_cloud import SpeechToTextV1 as SpeechToText
speech_to_text = SpeechToText(username='******',
password='******')
print(json.dumps(speech_to_text.models(), indent=2))
with open(join(dirname(__file__), '../resources/speech.wav'),
'rb') as audio_file:
print(
json.dumps(speech_to_text.recognize(audio_file,
content_type='audio/wav'),
indent=2))
def signal_handler(signal, frame):
global interrupted
interrupted = True
def interrupt_callback():
global interrupted
return interrupted
dotenv_path = join(dirname(__file__), '.env')
load_dotenv(dotenv_path)
model = os.environ.get("SNOWBOY_MODEL")
stt = SpeechToText(username=os.environ.get("STT_USERNAME"),
password=os.environ.get("STT_PASSWORD"))
workspace_id = os.environ.get("WORKSPACE_ID")
conversation = ConversationV1(username=os.environ.get("CONVERSATION_USERNAME"),
password=os.environ.get("CONVERSATION_PASSWORD"),
version='2016-02-11')
tts = TextToSpeechV1(username=os.environ.get("TTS_USERNAME"),
password=os.environ.get("TTS_PASSWORD"),
x_watson_learning_opt_out=True) # Optional flag
# Create NeoPixel object with appropriate configuration.
strip = Adafruit_NeoPixel(LED_COUNT, LED_PIN, LED_FREQ_HZ, LED_DMA, LED_INVERT,
LED_BRIGHTNESS)
# Intialize the library (must be called once before other functions).
def transcribe_audio(path_to_audio_file):
username = "******"
password = "******"
speech_to_text = SpeechToText(username=username, password=password)
with open(path_to_audio_file, 'rb') as audio_file:
return speech_to_text.recognize(audio_file, content_type='audio/wav')
def main():
try:
ser = serial.Serial('/dev/serial0', 9600, timeout=1)
ser.isOpen()
print("port is opened")
except IOError:
ser.close()
ser.open()
print("port was already open, was closed and opene again")
dotenv_path = join(dirname(__file__), '.env')
load_dotenv(dotenv_path)
stt = SpeechToText(username=os.environ.get("STT_USERNAME"),
password=os.environ.get("STT_PASSWORD"))
workspace_id = os.environ.get("WORKSPACE_ID")
conversation = ConversationV1(
username=os.environ.get("CONVERSATION_USERNAME"),
password=os.environ.get("CONVERSATION_PASSWORD"),
version='2016-09-20')
tone_analyzer = ToneAnalyzerV3(
username=os.environ.get("TONE_ANALYZER_USERNAME"),
password=os.environ.get("TONE_ANALYZER_PASSWORD"),
version='2016-02-11')
tts = TextToSpeechV1(username=os.environ.get("TTS_USERNAME"),
password=os.environ.get("TTS_PASSWORD"),
x_watson_learning_opt_out=True) # Optional flag
# Create NeoPixel object with appropriate configuration.
strip = Adafruit_NeoPixel(LED_COUNT, LED_PIN, LED_FREQ_HZ, LED_DMA,
LED_INVERT, LED_BRIGHTNESS)
# Intialize the library (must be called once before other functions).
strip.begin()
current_action = ''
msg_out = ''
while current_action != 'end_conversation':
message = listen(stt)
# emotion = get_emotion(tone_analyzer, message)
print(message)
response = send_message(conversation, workspace_id, message, "sad")
# Check for a text response from API
if response['output']['text']:
msg_out = response['output']['text'][0]
# Check for action flags sent by the dialog
if 'action' in response['output']:
current_action = response['output']['action']
# User asked what time is it, so we output the local system time
if current_action == 'display_time':
msg_out = 'The current time is ' + time.strftime('%I:%M %p')
current_action = ''
# User asked bot to turn red
if current_action == 'red':
msg_out = 'Turning Red'
for pix in range(0, strip.numPixels()):
strip.setPixelColor(pix, Color(255, 0, 0))
strip.show()
time.sleep(50 / 1000.0)
current_action = ''
# User asked bot to turn green
if current_action == 'green':
msg_out = 'Turning green'
for pix in range(0, strip.numPixels()):
strip.setPixelColor(pix, Color(0, 255, 0))
strip.show()
time.sleep(50 / 1000.0)
current_action = ''
# User asked bot to turn blue
if current_action == 'blue':
msg_out = 'Turning blue'
for pix in range(0, strip.numPixels()):
strip.setPixelColor(pix, Color(0, 0, 255))
strip.show()
time.sleep(50 / 1000.0)
current_action = ''
# User asked bot to turn disco
if current_action == 'disco':
msg_out = 'Turning disco'
theaterChaseRainbow(strip)
current_action = ''
# User asked bot to set rainbow color
if current_action == 'raibow':
msg_out = 'Turning rainbow'
RainbowCycle(strip)
current_action = ''
print(msg_out)
speak(tts, msg_out)
#recorder.play_from_file("output.wav")
ser.close()
def main():
try:
ser = serial.Serial('/dev/serial0', 9600, timeout=1)
ser.isOpen()
print ("port is opened")
except IOError:
ser.close()
ser.open()
print("port was already open, was closed and opene again")
dotenv_path = join(dirname(__file__), '.env')
load_dotenv(dotenv_path)
stt = SpeechToText(
username=os.environ.get("STT_USERNAME"),
password=os.environ.get("STT_PASSWORD"))
workspace_id = os.environ.get("WORKSPACE_ID")
conversation = ConversationV1(
username=os.environ.get("CONVERSATION_USERNAME"),
password=os.environ.get("CONVERSATION_PASSWORD"),
version='2016-09-20')
tone_analyzer = ToneAnalyzerV3(
username=os.environ.get("TONE_ANALYZER_USERNAME"),
password=os.environ.get("TONE_ANALYZER_PASSWORD"),
version='2016-02-11')
tts = TextToSpeechV1(
username=os.environ.get("TTS_USERNAME"),
password=os.environ.get("TTS_PASSWORD"),
x_watson_learning_opt_out=True) # Optional flag
current_action = ''
msg_out = ''
while current_action != 'end_conversation':
message = listen(stt)
# emotion = get_emotion(tone_analyzer, message)
print(message)
response = send_message(conversation, workspace_id, message, "sad")
# Check for a text response from API
if response['output']['text']:
msg_out = response['output']['text'][0]
# Check for action flags sent by the dialog
if 'action' in response['output']:
current_action = response['output']['action']
# User asked what time is it, so we output the local system time
if current_action == 'display_time':
msg_out = 'The current time is ' + time.strftime('%I:%M %p')
current_action = ''
# User asked robot to step forward
if current_action == 'step forward':
msg_out = 'Walking forward'
ser.write("1,1=".encode())
current_action = ''
# User asked robot to step back
if current_action == 'step back':
msg_out = 'stepping back'
ser.write("1,2=".encode())
current_action = ''
# User asked robot to move left
if current_action == 'step left':
msg_out = 'Moving to the left'
ser.write("1,5=".encode())
current_action = ''
# User asked robot to move right
if current_action == 'step right':
msg_out = 'moving to the right'
ser.write("1,6=".encode())
current_action = ''
# User asked robot to wave
if current_action == 'wave':
msg_out = 'Waving'
ser.write("2,2=".encode())
current_action = ''
print(msg_out)
speak(tts, msg_out)
#recorder.play_from_file("output.wav")
ser.close()
