def test_sync_recognize_content_with_optional_params_no_gax(self):
from base64 import b64encode
from google.cloud._helpers import _to_bytes
from google.cloud._helpers import _bytes_to_unicode
from google.cloud._testing import _Monkey
from google.cloud.speech import client as MUT
from google.cloud import speech
from google.cloud.speech.sample import Sample
from google.cloud.speech.transcript import Transcript
from unit_tests._fixtures import SYNC_RECOGNIZE_RESPONSE
_AUDIO_CONTENT = _to_bytes(self.AUDIO_CONTENT)
_B64_AUDIO_CONTENT = _bytes_to_unicode(b64encode(_AUDIO_CONTENT))
RETURNED = SYNC_RECOGNIZE_RESPONSE
REQUEST = {
'config': {
'encoding': 'FLAC',
'maxAlternatives': 2,
'sampleRate': 16000,
'speechContext': {
'phrases': [
'hi',
]
},
'languageCode': 'EN',
'profanityFilter': True,
},
'audio': {
'content': _B64_AUDIO_CONTENT,
}
}
credentials = _Credentials()
client = self._makeOne(credentials=credentials, use_gax=False)
client.connection = _Connection(RETURNED)
encoding = speech.Encoding.FLAC
sample = Sample(content=self.AUDIO_CONTENT, encoding=encoding,
sample_rate=self.SAMPLE_RATE)
with _Monkey(MUT, _USE_GAX=False):
response = client.sync_recognize(sample,
language_code='EN',
max_alternatives=2,
profanity_filter=True,
speech_context=self.HINTS)
self.assertEqual(len(client.connection._requested), 1)
req = client.connection._requested[0]
self.assertEqual(len(req), 3)
self.assertEqual(req['data'], REQUEST)
self.assertEqual(req['method'], 'POST')
self.assertEqual(req['path'], 'speech:syncrecognize')
alternative = SYNC_RECOGNIZE_RESPONSE['results'][0]['alternatives'][0]
expected = Transcript.from_api_repr(alternative)
self.assertEqual(len(response), 1)
self.assertIsInstance(response[0], Transcript)
self.assertEqual(response[0].transcript, expected.transcript)
self.assertEqual(response[0].confidence, expected.confidence)
def test_sync_recognize_source_uri_without_optional_params_no_gax(self):
from google.cloud._testing import _Monkey
from google.cloud.speech import client as MUT
from google.cloud import speech
from google.cloud.speech.sample import Sample
from google.cloud.speech.transcript import Transcript
from unit_tests._fixtures import SYNC_RECOGNIZE_RESPONSE
RETURNED = SYNC_RECOGNIZE_RESPONSE
REQUEST = {
'config': {
'encoding': 'FLAC',
'sampleRate': 16000,
},
'audio': {
'uri': self.AUDIO_SOURCE_URI,
}
}
credentials = _Credentials()
client = self._makeOne(credentials=credentials, use_gax=False)
client.connection = _Connection(RETURNED)
encoding = speech.Encoding.FLAC
sample = Sample(source_uri=self.AUDIO_SOURCE_URI,
encoding=encoding,
sample_rate=self.SAMPLE_RATE)
with _Monkey(MUT, _USE_GAX=False):
response = client.sync_recognize(sample)
self.assertEqual(len(client.connection._requested), 1)
req = client.connection._requested[0]
self.assertEqual(len(req), 3)
self.assertEqual(req['data'], REQUEST)
self.assertEqual(req['method'], 'POST')
self.assertEqual(req['path'], 'speech:syncrecognize')
expected = Transcript.from_api_repr(
SYNC_RECOGNIZE_RESPONSE['results'][0]['alternatives'][0])
self.assertEqual(len(response), 1)
self.assertIsInstance(response[0], Transcript)
self.assertEqual(response[0].transcript, expected.transcript)
self.assertEqual(response[0].confidence, expected.confidence)
def test_sync_recognize_source_uri_without_optional_params_no_gax(self):
from google.cloud._testing import _Monkey
from google.cloud.speech import client as MUT
from google.cloud import speech
from google.cloud.speech.sample import Sample
from google.cloud.speech.transcript import Transcript
from unit_tests._fixtures import SYNC_RECOGNIZE_RESPONSE
RETURNED = SYNC_RECOGNIZE_RESPONSE
REQUEST = {
'config': {
'encoding': 'FLAC',
'sampleRate': 16000,
},
'audio': {
'uri': self.AUDIO_SOURCE_URI,
}
}
credentials = _Credentials()
client = self._makeOne(credentials=credentials, use_gax=False)
client.connection = _Connection(RETURNED)
encoding = speech.Encoding.FLAC
sample = Sample(source_uri=self.AUDIO_SOURCE_URI, encoding=encoding,
sample_rate=self.SAMPLE_RATE)
with _Monkey(MUT, _USE_GAX=False):
response = client.sync_recognize(sample)
self.assertEqual(len(client.connection._requested), 1)
req = client.connection._requested[0]
self.assertEqual(len(req), 3)
self.assertEqual(req['data'], REQUEST)
self.assertEqual(req['method'], 'POST')
self.assertEqual(req['path'], 'speech:syncrecognize')
expected = Transcript.from_api_repr(
SYNC_RECOGNIZE_RESPONSE['results'][0]['alternatives'][0])
self.assertEqual(len(response), 1)
self.assertIsInstance(response[0], Transcript)
self.assertEqual(response[0].transcript, expected.transcript)
self.assertEqual(response[0].confidence, expected.confidence)
def _update(self, response):
"""Update Operation instance with latest data from Speech API.
.. _speech_operations: https://cloud.google.com/speech/reference/\
rest/v1beta1/operations
:type response: dict
:param response: Response from Speech API Operations endpoint.
See: `speech_operations`_.
"""
metadata = response.get('metadata', None)
raw_results = response.get('response', {}).get('results', None)
results = []
if raw_results:
for result in raw_results[0]['alternatives']:
results.append(Transcript.from_api_repr(result))
if metadata:
self._metadata = Metadata.from_api_repr(metadata)
self._results = results
self._complete = response.get('done', False)
def _update(self, response):
"""Update Operation instance with latest data from Speech API.
.. _speech_operations: https://cloud.google.com/speech/reference/\
rest/v1beta1/operations
:type response: dict
:param response: Response from Speech API Operations endpoint.
See: `speech_operations`_.
"""
metadata = response.get('metadata', None)
raw_results = response.get('response', {}).get('results', None)
results = []
if raw_results:
for result in raw_results[0]['alternatives']:
results.append(Transcript.from_api_repr(result))
if metadata:
self._metadata = Metadata.from_api_repr(metadata)
self._results = results
self._complete = response.get('done', False)
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']) == 1:
result = api_response['results'][0]
return [
Transcript.from_api_repr(alternative)
for alternative in result['alternatives']
]
else:
raise ValueError('More than one result or none returned from API.')
def test_sync_recognize_content_with_optional_params_no_gax(self):
from base64 import b64encode
from google.cloud._helpers import _to_bytes
from google.cloud._helpers import _bytes_to_unicode
from google.cloud._testing import _Monkey
from google.cloud.speech import client as MUT
from google.cloud import speech
from google.cloud.speech.sample import Sample
from google.cloud.speech.transcript import Transcript
from unit_tests._fixtures import SYNC_RECOGNIZE_RESPONSE
_AUDIO_CONTENT = _to_bytes(self.AUDIO_CONTENT)
_B64_AUDIO_CONTENT = _bytes_to_unicode(b64encode(_AUDIO_CONTENT))
RETURNED = SYNC_RECOGNIZE_RESPONSE
REQUEST = {
'config': {
'encoding': 'FLAC',
'maxAlternatives': 2,
'sampleRate': 16000,
'speechContext': {
'phrases': [
'hi',
]
},
'languageCode': 'EN',
'profanityFilter': True,
},
'audio': {
'content': _B64_AUDIO_CONTENT,
}
}
credentials = _Credentials()
client = self._makeOne(credentials=credentials, use_gax=False)
client.connection = _Connection(RETURNED)
encoding = speech.Encoding.FLAC
sample = Sample(content=self.AUDIO_CONTENT,
encoding=encoding,
sample_rate=self.SAMPLE_RATE)
with _Monkey(MUT, _USE_GAX=False):
response = client.sync_recognize(sample,
language_code='EN',
max_alternatives=2,
profanity_filter=True,
speech_context=self.HINTS)
self.assertEqual(len(client.connection._requested), 1)
req = client.connection._requested[0]
self.assertEqual(len(req), 3)
self.assertEqual(req['data'], REQUEST)
self.assertEqual(req['method'], 'POST')
self.assertEqual(req['path'], 'speech:syncrecognize')
alternative = SYNC_RECOGNIZE_RESPONSE['results'][0]['alternatives'][0]
expected = Transcript.from_api_repr(alternative)
self.assertEqual(len(response), 1)
self.assertIsInstance(response[0], Transcript)
self.assertEqual(response[0].transcript, expected.transcript)
self.assertEqual(response[0].confidence, expected.confidence)
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']) == 1:
result = api_response['results'][0]
return [Transcript.from_api_repr(alternative)
for alternative in result['alternatives']]
else:
raise ValueError('More than one result or none returned from API.')
