def _update_state(self, operation_pb):
"""Update the state of the current object based on operation.
This mostly does what the base class does, but all populates
results.
:type operation_pb:
:class:`~google.longrunning.operations_pb2.Operation`
:param operation_pb: Protobuf to be parsed.
:raises ValueError: If there are no ``results`` from the operation.
"""
super(Operation, self)._update_state(operation_pb)
result_type = operation_pb.WhichOneof('result')
if result_type != 'response':
return
# Retrieve the results.
# If there were no results at all, raise an exception.
pb_results = self.response.results
if len(pb_results) == 0:
raise ValueError('Speech API returned no results.')
# Save the results to the Operation object.
self.results = []
for pb_result in pb_results:
self.results.append(Result.from_pb(pb_result))
def sync_recognize(self, sample, language_code=None, max_alternatives=None,
profanity_filter=None, speech_context=None):
"""Synchronous Speech Recognition.
.. _sync_recognize: https://cloud.google.com/speech/reference/\
rest/v1beta1/speech/syncrecognize
See `sync_recognize`_.
:type sample: :class:`~google.cloud.speech.sample.Sample`
:param sample: Instance of ``Sample`` containing audio information.
:type language_code: str
:param language_code: (Optional) The language of the supplied audio as
BCP-47 language tag. Example: ``'en-GB'``.
If omitted, defaults to ``'en-US'``.
:type max_alternatives: int
:param max_alternatives: (Optional) Maximum number of recognition
hypotheses to be returned. The server may
return fewer than maxAlternatives.
Valid values are 0-30. A value of 0 or 1
will return a maximum of 1. Defaults to 1
:type profanity_filter: bool
:param profanity_filter: If True, the server will attempt to filter
out profanities, replacing all but the
initial character in each filtered word with
asterisks, e.g. ``'f***'``. If False or
omitted, profanities won't be filtered out.
:type speech_context: list
:param speech_context: A list of strings (max 50) containing words and
phrases "hints" so that the speech recognition
is more likely to recognize them. This can be
used to improve the accuracy for specific words
and phrases. This can also be used to add new
words to the vocabulary of the recognizer.
:rtype: list
:returns: List of :class:`google.cloud.speech.result.Result` objects.
:raises: ValueError if there are no results.
"""
config = RecognitionConfig(
encoding=sample.encoding, sample_rate=sample.sample_rate,
language_code=language_code, max_alternatives=max_alternatives,
profanity_filter=profanity_filter,
speech_context=SpeechContext(phrases=speech_context))
audio = RecognitionAudio(content=sample.content,
uri=sample.source_uri)
api = self._gapic_api
api_response = api.sync_recognize(config=config, audio=audio)
# Sanity check: If we got no results back, raise an error.
if len(api_response.results) == 0:
raise ValueError('No results returned from the Speech API.')
# Iterate over any results that came back.
return [Result.from_pb(result) for result in api_response.results]
def sync_recognize(self,
sample,
language_code=None,
max_alternatives=None,
profanity_filter=None,
speech_context=None):
"""Synchronous Speech Recognition.
.. _sync_recognize: https://cloud.google.com/speech/reference/\
rest/v1beta1/speech/syncrecognize
See `sync_recognize`_.
:type sample: :class:`~google.cloud.speech.sample.Sample`
:param sample: Instance of ``Sample`` containing audio information.
:type language_code: str
:param language_code: (Optional) The language of the supplied audio as
BCP-47 language tag. Example: ``'en-GB'``.
If omitted, defaults to ``'en-US'``.
:type max_alternatives: int
:param max_alternatives: (Optional) Maximum number of recognition
hypotheses to be returned. The server may
return fewer than maxAlternatives.
Valid values are 0-30. A value of 0 or 1
will return a maximum of 1. Defaults to 1
:type profanity_filter: bool
:param profanity_filter: If True, the server will attempt to filter
out profanities, replacing all but the
initial character in each filtered word with
asterisks, e.g. ``'f***'``. If False or
omitted, profanities won't be filtered out.
:type speech_context: list
:param speech_context: A list of strings (max 50) containing words and
phrases "hints" so that the speech recognition
is more likely to recognize them. This can be
used to improve the accuracy for specific words
and phrases. This can also be used to add new
words to the vocabulary of the recognizer.
:rtype: list
:returns: A list of dictionaries. One dict for each alternative. Each
dictionary typically contains two keys (though not
all will be present in all cases)
* ``transcript``: The detected text from the audio recording.
* ``confidence``: The confidence in language detection, float
between 0 and 1.
:raises: ValueError if more than one result is returned or no results.
"""
data = _build_request_data(sample, language_code, max_alternatives,
profanity_filter, speech_context)
api_response = self._connection.api_request(
method='POST', path='speech:syncrecognize', data=data)
if len(api_response['results']) > 0:
results = api_response['results']
return [Result.from_api_repr(result) for result in results]
else:
raise ValueError('No results were returned from the API')
