def do_translation_loop():
print("Begin speaking...")
client = media.SpeechTranslationServiceClient()
speech_config = media.TranslateSpeechConfig(
audio_encoding="linear16",
source_language_code="en-US",
target_language_code="es-ES",
)
config = media.StreamingTranslateSpeechConfig(audio_config=speech_config,
single_utterance=True)
# The first request contains the configuration.
# Note that audio_content is explicitly set to None.
first_request = media.StreamingTranslateSpeechRequest(
streaming_config=config)
with MicrophoneStream(RATE, CHUNK) as stream:
audio_generator = stream.generator()
mic_requests = (media.StreamingTranslateSpeechRequest(
audio_content=content) for content in audio_generator)
requests = itertools.chain(iter([first_request]), mic_requests)
responses = client.streaming_translate_speech(requests)
# Print the translation responses as they arrive
result = listen_print_loop(responses)
if result == 0:
stream.exit()
def do_translation_loop(configs, token, seq_count, session):
client = media.SpeechTranslationServiceClient()
speech_config = media.TranslateSpeechConfig(
audio_encoding='linear16',
source_language_code=configs["source_lang"],
target_language_code=configs["target_lang"])
config = media.StreamingTranslateSpeechConfig(audio_config=speech_config,
single_utterance=True)
# The first request contains the configuration.
# Note that audio_content is explicitly set to None.
first_request = media.StreamingTranslateSpeechRequest(
streaming_config=config, audio_content=None)
with MicrophoneStream(RATE, CHUNK, configs, token, seq_count,
session) as stream:
audio_generator = stream.generator()
mic_requests = (media.StreamingTranslateSpeechRequest(
audio_content=content, streaming_config=config)
for content in audio_generator)
requests = itertools.chain(iter([first_request]), mic_requests)
responses = client.streaming_translate_speech(requests)
# Print the translation responses as they arrive
result = listen_print_loop(responses, stream)
if result == 0:
stream.exit()
def main():
client = mediatranslation.SpeechTranslationServiceClient()
speech_config = mediatranslation.TranslateSpeechConfig(
audio_encoding='linear16',
source_language_code='en-US',
target_language_code='es-ES')
config = mediatranslation.StreamingTranslateSpeechConfig(
audio_config=speech_config)
# The first request contains the configuration.
# Note that audio_content is explicitly set to None.
first_request = mediatranslation.StreamingTranslateSpeechRequest(
streaming_config=config, audio_content=None)
with MicrophoneStream(RATE, CHUNK) as stream:
audio_generator = stream.generator()
mic_requests = (mediatranslation.StreamingTranslateSpeechRequest(
audio_content=content, streaming_config=config)
for content in audio_generator)
requests = itertools.chain(iter([first_request]), mic_requests)
responses = client.streaming_translate_speech(requests)
# Print the translation responses as they arrive
listen_print_loop(responses)
def do_translation_loop(args, projector, font, fontsize, log, interim):
dev_index = args.dev
lang = args.lang
for event in pygame.event.get():
if event.type == pygame.KEYDOWN and event.key == pygame.K_q:
log.write("-- CLEAN EXIT ---\n")
log.close()
exit(0)
elif event.type == pygame.KEYDOWN and event.key == pygame.K_c:
log.write("c pressed - clear screen\n")
log.flush()
projector.clear()
elif event.type == pygame.KEYDOWN and event.key == pygame.K_i:
interim = not interim
log.write("i pressed. Interim results: {}\n".format(interim))
log.flush()
else:
continue
client = media.SpeechTranslationServiceClient()
speech_config = media.TranslateSpeechConfig(audio_encoding='linear16',
source_language_code='en-US',
target_language_code=lang)
config = media.StreamingTranslateSpeechConfig(audio_config=speech_config,
single_utterance=True)
# The first request contains the configuration.
# Note that audio_content is explicitly set to None.
first_request = media.StreamingTranslateSpeechRequest(
streaming_config=config, audio_content=None)
with MicrophoneStream(RATE, CHUNK, dev_index) as stream:
audio_generator = stream.generator()
mic_requests = (media.StreamingTranslateSpeechRequest(
audio_content=content, streaming_config=config)
for content in audio_generator)
requests = itertools.chain(iter([first_request]), mic_requests)
responses = client.streaming_translate_speech(requests)
# Print the translation responses as they arrive
result = listen_print_loop(responses, args, projector, font, fontsize,
log, interim)
if result == 0:
stream.exit()
return interim
def translate_from_file(file_path='path/to/your/file'):
client = mediatranslation.SpeechTranslationServiceClient()
# The `sample_rate_hertz` field is not required for FLAC and WAV (Linear16)
# encoded data. Other audio encodings must provide the sampling rate.
audio_config = mediatranslation.TranslateSpeechConfig(
audio_encoding='linear16',
source_language_code='en-US',
target_language_code='fr-FR')
streaming_config = mediatranslation.StreamingTranslateSpeechConfig(
audio_config=audio_config)
def request_generator(config, audio_file_path):
# The first request contains the configuration.
# Note that audio_content is explicitly set to None.
yield mediatranslation.StreamingTranslateSpeechRequest(
streaming_config=config, audio_content=None)
with open(audio_file_path, 'rb') as audio:
while True:
chunk = audio.read(4096)
if not chunk:
break
yield mediatranslation.StreamingTranslateSpeechRequest(
audio_content=chunk,
streaming_config=config)
requests = request_generator(streaming_config, file_path)
responses = client.streaming_translate_speech(requests)
for response in responses:
# Once the transcription settles, the response contains the
# is_final result. The other results will be for subsequent portions of
# the audio.
result = response.result
translation = result.text_translation_result.translation
source = result.recognition_result
if result.text_translation_result.is_final:
print(u'\nFinal translation: {0}'.format(translation))
print(u'Final recognition result: {0}'.format(source))
break
print(u'\nPartial translation: {0}'.format(translation))
print(u'Partial recognition result: {0}'.format(source))