Alternate strategy,to just pass back responses.

Author: daspecster

docs/speech-streaming.rst

@@ -1,33 +1,23 @@
-Speech StreamingResponseContainer
-=================================
+Streaming Speech Response
+=========================
 
-.. automodule:: google.cloud.speech.streaming.container
+.. automodule:: google.cloud.speech.streaming_response
   :members:
   :undoc-members:
   :show-inheritance:
 
-Speech Streaming Request helpers
-================================
+Streaming Speech Result
+=======================
 
-.. automodule:: google.cloud.speech.streaming.request
+.. automodule:: google.cloud.speech.streaming_result
   :members:
   :undoc-members:
   :show-inheritance:
 
-Speech StreamingSpeechResponse
-==============================
+Streaming Endpointer Type
+=========================
 
-.. automodule:: google.cloud.speech.streaming.response
-  :members:
-  :undoc-members:
-  :show-inheritance:
-
-
-
-Speech StreamingSpeechResult
-============================
-
-.. automodule:: google.cloud.speech.streaming.result
+.. automodule:: google.cloud.speech.endpointer_type
   :members:
   :undoc-members:
   :show-inheritance:

docs/speech-usage.rst

@@ -51,10 +51,9 @@ See: `Speech Asynchronous Recognize`_
 
     >>> import time
     >>> from google.cloud import speech
-    >>> from google.cloud.speech.encoding import Encoding
     >>> client = speech.Client()
     >>> sample = client.sample(source_uri='gs://my-bucket/recording.flac',
-    ...                        encoding=Encoding.LINEAR16,
+    ...                        encoding=speech.Encoding.LINEAR16,
     ...                        sample_rate=44100)
     >>> operation = client.async_recognize(sample, max_alternatives=2)
     >>> retry_count = 100
@@ -82,10 +81,9 @@ Great Britian.
 .. code-block:: python
 
     >>> from google.cloud import speech
-    >>> from google.cloud.speech.encoding import Encoding
     >>> client = speech.Client()
     >>> sample = client.sample(source_uri='gs://my-bucket/recording.flac',
-    ...                        encoding=Encoding.FLAC,
+    ...                        encoding=speech.Encoding.FLAC,
     ...                        sample_rate=44100)
     >>> operation = client.async_recognize(sample, max_alternatives=2)
      >>> alternatives = client.sync_recognize(
@@ -107,10 +105,9 @@ Example of using the profanity filter.
 .. code-block:: python
 
     >>> from google.cloud import speech
-    >>> from google.cloud.speech.encoding import Encoding
     >>> client = speech.Client()
     >>> sample = client.sample(source_uri='gs://my-bucket/recording.flac',
-    ...                        encoding=Encoding.FLAC,
+    ...                        encoding=speech.Encoding.FLAC,
     ...                        sample_rate=44100)
     >>> alternatives = client.sync_recognize(sample, max_alternatives=1,
     ...                                      profanity_filter=True)
@@ -129,10 +126,9 @@ words to the vocabulary of the recognizer.
 .. code-block:: python
 
     >>> from google.cloud import speech
-    >>> from google.cloud.speech.encoding import Encoding
     >>> client = speech.Client()
     >>> sample = client.sample(source_uri='gs://my-bucket/recording.flac',
-    ...                        encoding=Encoding.FLAC,
+    ...                        encoding=speech.Encoding.FLAC,
     ...                        sample_rate=44100)
     >>> hints = ['hi', 'good afternoon']
     >>> alternatives = client.sync_recognize(sample, max_alternatives=2,
@@ -161,12 +157,11 @@ data to possible text alternatives on the fly.
 
     >>> import io
     >>> from google.cloud import speech
-    >>> from google.cloud.speech.encoding import Encoding
     >>> client = speech.Client()
     >>> with io.open('./hello.wav', 'rb') as stream:
-    >>>     sample = client.sample(stream=stream, encoding=Encoding.LINEAR16,
+    ...     sample = client.sample(stream=stream, encoding=speech.Encoding.LINEAR16,
     ...                            sample_rate=16000)
-    >>>     for response in client.stream_recognize(sample):
+    ...     for response in client.stream_recognize(sample):
     ...         print(response.transcript)
     hello
     ...         print(response.is_final)
@@ -182,12 +177,11 @@ result(s) are returned.
 
     >>> import io
     >>> from google.cloud import speech
-    >>> from google.cloud.speech.encoding import Encoding
     >>> client = speech.Client()
     >>> with io.open('./hello.wav', 'rb') as stream:
-    >>>     sample = client.sample(stream=stream, encoding=Encoding.LINEAR16,
+    >>>     sample = client.sample(stream=stream, encoding=speech.Encoding.LINEAR16,
     ...                            sample_rate=16000)
-    >>>     for response in client.stream_recognize(sample,
+    ...     for response in client.stream_recognize(sample,
     ...                                             interim_results=True):
     ...         print(response.transcript)
     hell
@@ -211,9 +205,9 @@ See: `Single Utterance`_
 .. code-block:: python
 
     >>> with io.open('./hello_pause_goodbye.wav', 'rb') as stream:
-    >>>     sample = client.sample(stream=stream, encoding=Encoding.LINEAR16,
+    >>>     sample = client.sample(stream=stream, encoding=speech.Encoding.LINEAR16,
     ...                            sample_rate=16000)
-    >>>     stream_container = client.stream_recognize(sample,
+    ...     stream_container = client.stream_recognize(sample,
     ...                                                single_utterance=True)
     >>> print(stream_container.get_full_text())
     hello

speech/google/cloud/speech/__init__.py

@@ -16,3 +16,4 @@
 
 from google.cloud.speech.client import Client
 from google.cloud.speech.connection import Connection
+from google.cloud.speech.encoding import Encoding

speech/google/cloud/speech/client.py

@@ -24,12 +24,17 @@
 from google.cloud.speech.connection import Connection
 from google.cloud.speech.encoding import Encoding
 from google.cloud.speech.operation import Operation
-from google.cloud.speech.streaming.request import _make_request_stream
 from google.cloud.speech.sample import Sample
-from google.cloud.speech.streaming.response import StreamingSpeechResponse
+from google.cloud.speech.streaming_response import StreamingSpeechResponse
 
 try:
     from google.cloud.gapic.speech.v1beta1.speech_api import SpeechApi
+    from google.cloud.grpc.speech.v1beta1.cloud_speech_pb2 import (
+        RecognitionConfig)
+    from google.cloud.grpc.speech.v1beta1.cloud_speech_pb2 import (
+        StreamingRecognitionConfig)
+    from google.cloud.grpc.speech.v1beta1.cloud_speech_pb2 import (
+        StreamingRecognizeRequest)
 except ImportError:  # pragma: NO COVER
     _HAVE_GAX = False
 else:
@@ -284,16 +289,9 @@ def stream_recognize(self, sample, language_code=None,
                                 with the is_final=false flag). If false or
                                 omitted, only is_final=true result(s) are
                                 returned.
-
-        :rtype: :class:`~streaming.StreamingResponseContainer`
-        :returns: An instance of ``StreamingReponseContainer``.
-
         """
         if not _USE_GAX:
-            raise EnvironmentError('GRPC is required to use this API.')
-
-        if sample.stream.closed:
-            raise ValueError('Stream is closed.')
+            raise EnvironmentError('gRPC is required to use this API.')
 
         requests = _make_request_stream(sample, language_code=language_code,
                                         max_alternatives=max_alternatives,
@@ -379,3 +377,160 @@ def _build_request_data(sample, language_code=None, max_alternatives=None,
     }
 
     return data
+
+
+def _make_request_stream(sample, language_code=None, max_alternatives=None,
+                         profanity_filter=None, speech_context=None,
+                         single_utterance=None, interim_results=None):
+    """Generate stream of requests from sample.
+
+    :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.
+
+    :type single_utterance: boolean
+    :param single_utterance: [Optional] If false or omitted, the recognizer
+                             will perform continuous recognition
+                             (continuing to process audio even if the user
+                             pauses speaking) until the client closes the
+                             output stream (gRPC API) or when the maximum
+                             time limit has been reached. Multiple
+                             SpeechRecognitionResults with the is_final
+                             flag set to true may be returned.
+
+                             If true, the recognizer will detect a single
+                             spoken utterance. When it detects that the
+                             user has paused or stopped speaking, it will
+                             return an END_OF_UTTERANCE event and cease
+                             recognition. It will return no more than one
+                             SpeechRecognitionResult with the is_final flag
+                             set to true.
+
+    :type interim_results: boolean
+    :param interim_results: [Optional] If true, interim results (tentative
+                            hypotheses) may be returned as they become
+                            available (these interim results are indicated
+                            with the is_final=false flag). If false or
+                            omitted, only is_final=true result(s) are
+                            returned.
+    """
+    config_request = _make_streaming_config(
+        sample, language_code=language_code, max_alternatives=max_alternatives,
+        profanity_filter=profanity_filter, speech_context=speech_context,
+        single_utterance=single_utterance, interim_results=interim_results)
+
+    # The config request MUST go first and not contain any audio data.
+    yield config_request
+
+    while True:
+        data = sample.stream.read(sample.chunk_size)
+        if not data:
+            break
+        # Optimize the request data size to around 100ms.
+        yield StreamingRecognizeRequest(audio_content=data)
+
+
+def _make_streaming_config(sample, language_code,
+                           max_alternatives, profanity_filter,
+                           speech_context, single_utterance,
+                           interim_results):
+    """Build streaming configuration.
+
+    :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.
+
+    :type single_utterance: boolean
+    :param single_utterance: [Optional] If false or omitted, the recognizer
+                             will perform continuous recognition
+                             (continuing to process audio even if the user
+                             pauses speaking) until the client closes the
+                             output stream (gRPC API) or when the maximum
+                             time limit has been reached. Multiple
+                             SpeechRecognitionResults with the is_final
+                             flag set to true may be returned.
+
+                             If true, the recognizer will detect a single
+                             spoken utterance. When it detects that the
+                             user has paused or stopped speaking, it will
+                             return an END_OF_UTTERANCE event and cease
+                             recognition. It will return no more than one
+                             SpeechRecognitionResult with the is_final flag
+                             set to true.
+
+    :type interim_results: boolean
+    :param interim_results: [Optional] If true, interim results (tentative
+                            hypotheses) may be returned as they become
+                            available (these interim results are indicated
+                            with the is_final=false flag). If false or
+                            omitted, only is_final=true result(s) are
+                            returned.
+
+    :rtype: :class:`~StreamingRecognitionConfig`
+    :returns: Instance of ``StreamingRecognitionConfig``.
+    """
+    config = RecognitionConfig(
+        encoding=sample.encoding, sample_rate=sample.sample_rate,
+        language_code=language_code, max_alternatives=max_alternatives,
+        profanity_filter=profanity_filter, speech_context=speech_context)
+
+    streaming_config = StreamingRecognitionConfig(
+        config=config, single_utterance=single_utterance,
+        interim_results=interim_results)
+
+    config_request = StreamingRecognizeRequest(
+        streaming_config=streaming_config)
+
+    return config_request

speech/google/cloud/speech/streaming/__init__.py renamed to speech/google/cloud/speech/endpointer_type.py

@@ -52,7 +52,7 @@ class Sample(object):
 
     def __init__(self, content=None, source_uri=None, stream=None,
                  encoding=None, sample_rate=None):
-        if [content, source_uri, stream].count(None) != 2:
+        if (content, source_uri, stream).count(None) != 2:
             raise ValueError('Supply only one of \'content\', \'source_uri\''
                              ' or stream.')