def process(self, loop):
"""
Audio stream recognition and result parsing
"""
#You can add speech contexts for better recognition
cap_speech_context = types.SpeechContext(**self.context)
metadata = types.RecognitionMetadata(**self.metadata)
client = speech.SpeechClient()
config = types.RecognitionConfig(encoding=self.encoding,
sample_rate_hertz=self.rate,
language_code=self.language,
speech_contexts=[
cap_speech_context,
],
enable_automatic_punctuation=True,
model=self.model,
metadata=metadata)
streaming_config = types.StreamingRecognitionConfig(
config=config,
interim_results=self.interim_results,
single_utterance=self.single_utterance)
audio_generator = self.stream_generator()
requests = iter(
types.StreamingRecognizeRequest(audio_content=content)
for content in audio_generator)
responses = client.streaming_recognize(streaming_config, requests)
#print('process',type(responses))
try:
#print('process')
for response in responses:
#print('process received')
if self.terminated:
break
if not response.results:
continue
result = response.results[0]
if not result.alternatives:
continue
speechData = MessageToDict(response)
global_async_worker.add_task(self.async_callback(speechData))
# debug
transcript = result.alternatives[0].transcript
print('>>', transcript, "(OK)" if result.is_final else "")
except Exception as e:
print('process excepted', e)
self.start()
def gspeech_client(self):
"""Creates the Google Speech API client, configures it, and sends/gets
audio/text data for parsing.
"""
language_code = 'en-US'
# Hints for the API
context = types.SpeechContext(phrases=self.context)
client = speech.SpeechClient()
# Create metadata object, helps processing
metadata = types.RecognitionMetadata()
# Interaction Type:
# VOICE_SEARCH: Transcribe spoken questions and queries into text.
# VOICE_COMMAND: Transcribe voice commands, such as for controlling a device.
metadata.interaction_type = (
enums.RecognitionMetadata.InteractionType.VOICE_COMMAND)
# Microphone Distance:
# NEARFIELD: The audio was captured from a closely placed microphone.
# MIDFIELD: The speaker is within 3 meters of the microphone.
# FARFIELD: The speaker is more than 3 meters away from the microphone.
metadata.microphone_distance = (
enums.RecognitionMetadata.MicrophoneDistance.MIDFIELD)
# Device Type:
# PC: Speech was recorded using a personal computer or tablet.
# VEHICLE: Speech was recorded in a vehicle.
# OTHER_OUTDOOR_DEVICE: Speech was recorded outdoors.
# OTHER_INDOOR_DEVICE: Speech was recorded indoors.
metadata.recording_device_type = (
enums.RecognitionMetadata.RecordingDeviceType.PC)
# Media Type:
# AUDIO: The speech data is an audio recording.
# VIDEO: The speech data originally recorded on a video.
metadata.original_media_type = (
enums.RecognitionMetadata.OriginalMediaType.AUDIO)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code=language_code,
speech_contexts=[context],
use_enhanced=True,
model='command_and_search',
metadata=metadata)
streaming_config = types.StreamingRecognitionConfig(
config=config, single_utterance=False, interim_results=False)
# Hack from Google Speech Python docs, very pythonic c:
requests = (types.StreamingRecognizeRequest(audio_content=content)
for content in self.generator())
responses = client.streaming_recognize(streaming_config, requests)
self._listen_print_loop(responses)