def detect_intent_stream(project_id, session_id, audio_file_path,
language_code):
"""Returns the result of detect intent with streaming audio as input.
Using the same `session_id` between requests allows continuation
of the conversation."""
from google.cloud import dialogflow
session_client = dialogflow.SessionsClient()
# Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
audio_encoding = dialogflow.AudioEncoding.AUDIO_ENCODING_LINEAR_16
sample_rate_hertz = 16000
session_path = session_client.session_path(project_id, session_id)
print('Session path: {}\n'.format(session_path))
def request_generator(audio_config, audio_file_path):
query_input = dialogflow.QueryInput(audio_config=audio_config)
# The first request contains the configuration.
yield dialogflow.StreamingDetectIntentRequest(session=session_path,
query_input=query_input)
# Here we are reading small chunks of audio data from a local
# audio file. In practice these chunks should come from
# an audio input device.
with open(audio_file_path, 'rb') as audio_file:
while True:
chunk = audio_file.read(4096)
if not chunk:
break
# The later requests contains audio data.
yield dialogflow.StreamingDetectIntentRequest(
input_audio=chunk)
audio_config = dialogflow.InputAudioConfig(
audio_encoding=audio_encoding,
language_code=language_code,
sample_rate_hertz=sample_rate_hertz)
requests = request_generator(audio_config, audio_file_path)
responses = session_client.streaming_detect_intent(requests=requests)
print('=' * 20)
for response in responses:
print('Intermediate transcript: "{}".'.format(
response.recognition_result.transcript))
# Note: The result from the last response is the final transcript along
# with the detected content.
query_result = response.query_result
print('=' * 20)
print('Query text: {}'.format(query_result.query_text))
print('Detected intent: {} (confidence: {})\n'.format(
query_result.intent.display_name,
query_result.intent_detection_confidence))
print('Fulfillment text: {}\n'.format(query_result.fulfillment_text))
def detect_intent_audio(project_id, session_id, audio_file_path,
language_code):
"""Returns the result of detect intent with an audio file as input.
Using the same `session_id` between requests allows continuation
of the conversation."""
from google.cloud import dialogflow
session_client = dialogflow.SessionsClient()
# Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
audio_encoding = dialogflow.AudioEncoding.AUDIO_ENCODING_LINEAR_16
sample_rate_hertz = 16000
session = session_client.session_path(project_id, session_id)
print("Session path: {}\n".format(session))
with open(audio_file_path, "rb") as audio_file:
input_audio = audio_file.read()
audio_config = dialogflow.InputAudioConfig(
audio_encoding=audio_encoding,
language_code=language_code,
sample_rate_hertz=sample_rate_hertz,
)
query_input = dialogflow.QueryInput(audio_config=audio_config)
request = dialogflow.DetectIntentRequest(
session=session,
query_input=query_input,
input_audio=input_audio,
)
response = session_client.detect_intent(request=request)
print("=" * 20)
print("Query text: {}".format(response.query_result.query_text))
print("Detected intent: {} (confidence: {})\n".format(
response.query_result.intent.display_name,
response.query_result.intent_detection_confidence,
))
print("Fulfillment text: {}\n".format(
response.query_result.fulfillment_text))
def runDetectIntent(self, session_id):
print("run detect intent")
self._isIntentDetect = True
session_client = dialogflow.SessionsClient()
audio_encoding = dialogflow.AudioEncoding.AUDIO_ENCODING_LINEAR_16
sample_rate_hertz = 16000
language_code = 'ru-RU'
session_id = '{}'.format(session_id)
print("session #{}".format(session_id))
session_path = session_client.session_path(self._project_id,
session_id)
print('Session path: {}\n'.format(session_path))
def _audio_callback_intent(in_data, frame_count, time_info, status):
if not self._is_playing:
self._buff.put(in_data)
return None, pyaudio.paContinue
try:
num_channels = 1
audio_format = pyaudio.paInt16
frame_length = 4096
audio_config = dialogflow.InputAudioConfig(
audio_encoding=audio_encoding,
language_code=language_code,
sample_rate_hertz=sample_rate_hertz)
self._pa = pyaudio.PyAudio()
self._audio_stream = self._pa.open(
rate=sample_rate_hertz,
channels=num_channels,
format=audio_format,
input=True,
frames_per_buffer=frame_length,
input_device_index=self._input_device_index,
stream_callback=_audio_callback_intent)
self._audio_stream.start_stream()
print("Waiting for command ...\n")
def request_generator(audio_config):
query_input = dialogflow.QueryInput(audio_config=audio_config)
output_audio_config = dialogflow.OutputAudioConfig(
audio_encoding=dialogflow.OutputAudioEncoding.
OUTPUT_AUDIO_ENCODING_LINEAR_16)
# The first request contains the configuration.
yield dialogflow.StreamingDetectIntentRequest(
session=session_path,
query_input=query_input,
single_utterance=True,
output_audio_config=output_audio_config)
while True:
chunk = self._buff.get()
if chunk is None:
print("chunk none")
return
if not self._isIntentDetect:
print("done intent")
return
yield dialogflow.StreamingDetectIntentRequest(
input_audio=chunk)
requests = request_generator(audio_config)
responses = session_client.streaming_detect_intent(requests)
print('=' * 20)
self._isEndConversation = True
for response in responses:
self.handleDialogflowResponse(response)
self.stopDetectIntent()
if self._isEndConversation:
print('end conversation')
print("send mqtt end detectinetnt event")
self._mqtt.publish(self._endDetectIntentEventTopic, "1")
self.runDetectHotword()
else:
self.playSound(self._wake_sound_file)
print('conversation continue')
self.runDetectIntent(session_id)
except KeyboardInterrupt:
print('stopping ...')
finally:
if self._audio_stream is not None:
self._audio_stream.stop_stream()
self._audio_stream.close()
# delete Porcupine last to avoid segfault in callback.
if self._porcupine is not None:
self._porcupine.delete()
def __init__(self):
rospy.init_node('dialogflow_node')
self.project_id = "folke-jkih"
self.session_id = str(uuid.uuid4())
self.language = rospy.get_param('~default_language', 'sv')
self.disable_audio = rospy.get_param('~disable_audio', False)
time_before_start = rospy.get_param('~time_before_start', 0.8)
self.save_audio_requests = rospy.get_param('~save_audio_requests',
True)
self.session_client = dialogflow.SessionsClient()
self.query_params = dialogflow.QueryParameters(
geo_location=latlng_pb2.LatLng(latitude=58.4106611,
longitude=15.6198244),
contexts=[
dialogflow.Context(lifespan_count=100,
name="projects/" + self.project_id +
"/agent/sessions/" + self.session_id +
"/contexts/linkoping")
])
self.audio_chunk_queue = deque(
maxlen=int(time_before_start * 31.25)
) # 16000/512 = 31.25, # Times 7.8 since the data is sent in 7.8Hz (16000 / 2048)
# Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
audio_encoding = dialogflow.AudioEncoding.AUDIO_ENCODING_LINEAR_16
sample_rate_hertz = 16000
self.audio_config = dialogflow.InputAudioConfig(
audio_encoding=audio_encoding,
language_code=self.language,
sample_rate_hertz=sample_rate_hertz,
single_utterance=True)
self.query_result_pub = rospy.Publisher('response',
Response,
queue_size=2)
self.query_text_pub = rospy.Publisher('query_text',
String,
queue_size=2)
self.transcript_pub = rospy.Publisher('transcript',
String,
queue_size=2)
self.fulfillment_pub = rospy.Publisher('fulfillment_text',
String,
queue_size=10)
self.is_listening_pub = rospy.Publisher('is_listening',
Bool,
queue_size=2,
latch=True)
self.is_waiting_for_hot_word = rospy.Publisher('waiting_for_hot_word',
Bool,
queue_size=2,
latch=True)
self.volume = 0
self.is_talking = False
self.is_in_dialog = False
self.detected_wake_word = False
self.head_visible = False
self.waiting_for_wake_word = False
self.cancel_stream_intent = False
self.skip_audio = False
rospy.wait_for_service('/qt_robot/audio/play')
self.audio_play_srv = rospy.ServiceProxy('/qt_robot/audio/play',
audio_play)
rospy.wait_for_service('/qt_robot/speech/config')
self.speech_config_srv = rospy.ServiceProxy('/qt_robot/speech/config',
speech_config)
rospy.Subscriber('text', String, self.text_callback)
rospy.Subscriber('is_talking', Bool, self.is_talking_callback)
rospy.Subscriber('event', Event, self.event_callback)
rospy.Subscriber('head_visible', Bool, self.head_visible_callback)
rospy.Subscriber('detected_wake_word', String,
self.detected_wake_word_callback)
rospy.Subscriber('end_of_conversation', EmptyMsg,
self.end_of_conversation_callback)
if not self.disable_audio:
rospy.Subscriber('sound', AudioData, self.audio_callback)
rospy.Subscriber('volume', UInt16, self.volume_callback)
self.list_intents_sevice = rospy.Service('list_intents', Empty,
self.handle_list_intents)
self.list_context_sevice = rospy.Service('list_context', Empty,
self.handle_list_context)
self.list_context_sevice = rospy.Service('clear_context', Empty,
self.handle_clear_context)
