Fix client_info bug, update docstrings and timeouts. (#6421)

speech/google/cloud/speech_v1/gapic/enums.py

@@ -25,51 +25,51 @@ class AudioEncoding(enum.IntEnum):
 
         All encodings support only 1 channel (mono) audio.
 
-        For best results, the audio source should be captured and transmitted using
-        a lossless encoding (``FLAC`` or ``LINEAR16``). The accuracy of the speech
-        recognition can be reduced if lossy codecs are used to capture or transmit
-        audio, particularly if background noise is present. Lossy codecs include
-        ``MULAW``, ``AMR``, ``AMR_WB``, ``OGG_OPUS``, and ``SPEEX_WITH_HEADER_BYTE``.
+        For best results, the audio source should be captured and transmitted
+        using a lossless encoding (``FLAC`` or ``LINEAR16``). The accuracy of
+        the speech recognition can be reduced if lossy codecs are used to
+        capture or transmit audio, particularly if background noise is present.
+        Lossy codecs include ``MULAW``, ``AMR``, ``AMR_WB``, ``OGG_OPUS``, and
+        ``SPEEX_WITH_HEADER_BYTE``.
 
-        The ``FLAC`` and ``WAV`` audio file formats include a header that describes the
-        included audio content. You can request recognition for ``WAV`` files that
-        contain either ``LINEAR16`` or ``MULAW`` encoded audio.
-        If you send ``FLAC`` or ``WAV`` audio file format in
-        your request, you do not need to specify an ``AudioEncoding``; the audio
-        encoding format is determined from the file header. If you specify
-        an ``AudioEncoding`` when you send  send ``FLAC`` or ``WAV`` audio, the
+        The ``FLAC`` and ``WAV`` audio file formats include a header that
+        describes the included audio content. You can request recognition for
+        ``WAV`` files that contain either ``LINEAR16`` or ``MULAW`` encoded
+        audio. If you send ``FLAC`` or ``WAV`` audio file format in your
+        request, you do not need to specify an ``AudioEncoding``; the audio
+        encoding format is determined from the file header. If you specify an
+        ``AudioEncoding`` when you send send ``FLAC`` or ``WAV`` audio, the
         encoding configuration must match the encoding described in the audio
         header; otherwise the request returns an
         ``google.rpc.Code.INVALID_ARGUMENT`` error code.
 
         Attributes:
           ENCODING_UNSPECIFIED (int): Not specified.
           LINEAR16 (int): Uncompressed 16-bit signed little-endian samples (Linear PCM).
-          FLAC (int): ``FLAC`` (Free Lossless Audio
-          Codec) is the recommended encoding because it is
-          lossless--therefore recognition is not compromised--and
-          requires only about half the bandwidth of ``LINEAR16``. ``FLAC`` stream
-          encoding supports 16-bit and 24-bit samples, however, not all fields in
+          FLAC (int): ``FLAC`` (Free Lossless Audio Codec) is the recommended encoding because
+          it is lossless--therefore recognition is not compromised--and requires
+          only about half the bandwidth of ``LINEAR16``. ``FLAC`` stream encoding
+          supports 16-bit and 24-bit samples, however, not all fields in
           ``STREAMINFO`` are supported.
           MULAW (int): 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
-          AMR (int): Adaptive Multi-Rate Narrowband codec. ``sample_rate_hertz`` must be 8000.
+          AMR (int): Adaptive Multi-Rate Narrowband codec. ``sample_rate_hertz`` must be
+          8000.
           AMR_WB (int): Adaptive Multi-Rate Wideband codec. ``sample_rate_hertz`` must be 16000.
           OGG_OPUS (int): Opus encoded audio frames in Ogg container
-          (`OggOpus <https://wiki.xiph.org/OggOpus>`_).
-          ``sample_rate_hertz`` must be one of 8000, 12000, 16000, 24000, or 48000.
+          (`OggOpus <https://wiki.xiph.org/OggOpus>`__). ``sample_rate_hertz``
+          must be one of 8000, 12000, 16000, 24000, or 48000.
           SPEEX_WITH_HEADER_BYTE (int): Although the use of lossy encodings is not recommended, if a very low
           bitrate encoding is required, ``OGG_OPUS`` is highly preferred over
-          Speex encoding. The `Speex <https://speex.org/>`_  encoding supported by
+          Speex encoding. The `Speex <https://speex.org/>`__ encoding supported by
           Cloud Speech API has a header byte in each block, as in MIME type
-          ``audio/x-speex-with-header-byte``.
-          It is a variant of the RTP Speex encoding defined in
-          `RFC 5574 <https://tools.ietf.org/html/rfc5574>`_.
+          ``audio/x-speex-with-header-byte``. It is a variant of the RTP Speex
+          encoding defined in `RFC 5574 <https://tools.ietf.org/html/rfc5574>`__.
           The stream is a sequence of blocks, one block per RTP packet. Each block
-          starts with a byte containing the length of the block, in bytes, followed
-          by one or more frames of Speex data, padded to an integral number of
-          bytes (octets) as specified in RFC 5574. In other words, each RTP header
-          is replaced with a single byte containing the block length. Only Speex
-          wideband is supported. ``sample_rate_hertz`` must be 16000.
+          starts with a byte containing the length of the block, in bytes,
+          followed by one or more frames of Speex data, padded to an integral
+          number of bytes (octets) as specified in RFC 5574. In other words, each
+          RTP header is replaced with a single byte containing the block length.
+          Only Speex wideband is supported. ``sample_rate_hertz`` must be 16000.
         """
         ENCODING_UNSPECIFIED = 0
         LINEAR16 = 1
@@ -92,9 +92,10 @@ class SpeechEventType(enum.IntEnum):
           speech utterance and expects no additional speech. Therefore, the server
           will not process additional audio (although it may subsequently return
           additional results). The client should stop sending additional audio
-          data, half-close the gRPC connection, and wait for any additional results
-          until the server closes the gRPC connection. This event is only sent if
-          ``single_utterance`` was set to ``true``, and is not used otherwise.
+          data, half-close the gRPC connection, and wait for any additional
+          results until the server closes the gRPC connection. This event is only
+          sent if ``single_utterance`` was set to ``true``, and is not used
+          otherwise.
         """
         SPEECH_EVENT_UNSPECIFIED = 0
         END_OF_SINGLE_UTTERANCE = 1

speech/google/cloud/speech_v1/gapic/speech_client.py

@@ -138,9 +138,10 @@ def __init__(self,
             )
 
         if client_info is None:
-            client_info = (
-                google.api_core.gapic_v1.client_info.DEFAULT_CLIENT_INFO)
-        client_info.gapic_version = _GAPIC_LIBRARY_VERSION
+            client_info = google.api_core.gapic_v1.client_info.ClientInfo(
+                gapic_version=_GAPIC_LIBRARY_VERSION, )
+        else:
+            client_info.gapic_version = _GAPIC_LIBRARY_VERSION
         self._client_info = client_info
 
         # Parse out the default settings for retry and timeout for each RPC
@@ -185,9 +186,11 @@ def recognize(self,
         Args:
             config (Union[dict, ~google.cloud.speech_v1.types.RecognitionConfig]): *Required* Provides information to the recognizer that specifies how to
                 process the request.
+
                 If a dict is provided, it must be of the same form as the protobuf
                 message :class:`~google.cloud.speech_v1.types.RecognitionConfig`
             audio (Union[dict, ~google.cloud.speech_v1.types.RecognitionAudio]): *Required* The audio data to be recognized.
+
                 If a dict is provided, it must be of the same form as the protobuf
                 message :class:`~google.cloud.speech_v1.types.RecognitionAudio`
             retry (Optional[google.api_core.retry.Retry]):  A retry object used
@@ -235,8 +238,8 @@ def long_running_recognize(self,
         """
         Performs asynchronous speech recognition: receive results via the
         google.longrunning.Operations interface. Returns either an
-        ``Operation.error`` or an ``Operation.response`` which contains
-        a ``LongRunningRecognizeResponse`` message.
+        ``Operation.error`` or an ``Operation.response`` which contains a
+        ``LongRunningRecognizeResponse`` message.
 
         Example:
             >>> from google.cloud import speech_v1
@@ -265,9 +268,11 @@ def long_running_recognize(self,
         Args:
             config (Union[dict, ~google.cloud.speech_v1.types.RecognitionConfig]): *Required* Provides information to the recognizer that specifies how to
                 process the request.
+
                 If a dict is provided, it must be of the same form as the protobuf
                 message :class:`~google.cloud.speech_v1.types.RecognitionConfig`
             audio (Union[dict, ~google.cloud.speech_v1.types.RecognitionAudio]): *Required* The audio data to be recognized.
+
                 If a dict is provided, it must be of the same form as the protobuf
                 message :class:`~google.cloud.speech_v1.types.RecognitionAudio`
             retry (Optional[google.api_core.retry.Retry]):  A retry object used

speech/google/cloud/speech_v1/gapic/speech_client_config.py

@@ -18,17 +18,17 @@
             },
             "methods": {
                 "Recognize": {
-                    "timeout_millis": 1000000,
+                    "timeout_millis": 200000,
                     "retry_codes_name": "idempotent",
                     "retry_params_name": "default"
                 },
                 "LongRunningRecognize": {
-                    "timeout_millis": 60000,
+                    "timeout_millis": 200000,
                     "retry_codes_name": "non_idempotent",
                     "retry_params_name": "default"
                 },
                 "StreamingRecognize": {
-                    "timeout_millis": 1000000,
+                    "timeout_millis": 200000,
                     "retry_codes_name": "idempotent",
                     "retry_params_name": "default"
                 }

speech/google/cloud/speech_v1/gapic/transports/speech_grpc_transport.py

@@ -118,8 +118,8 @@ def long_running_recognize(self):
 
         Performs asynchronous speech recognition: receive results via the
         google.longrunning.Operations interface. Returns either an
-        ``Operation.error`` or an ``Operation.response`` which contains
-        a ``LongRunningRecognizeResponse`` message.
+        ``Operation.error`` or an ``Operation.response`` which contains a
+        ``LongRunningRecognizeResponse`` message.
 
         Returns:
             Callable: A callable which accepts the appropriate

speech/google/cloud/speech_v1p1beta1/gapic/enums.py

@@ -25,51 +25,51 @@ class AudioEncoding(enum.IntEnum):
 
         All encodings support only 1 channel (mono) audio.
 
-        For best results, the audio source should be captured and transmitted using
-        a lossless encoding (``FLAC`` or ``LINEAR16``). The accuracy of the speech
-        recognition can be reduced if lossy codecs are used to capture or transmit
-        audio, particularly if background noise is present. Lossy codecs include
-        ``MULAW``, ``AMR``, ``AMR_WB``, ``OGG_OPUS``, and ``SPEEX_WITH_HEADER_BYTE``.
-
-        The ``FLAC`` and ``WAV`` audio file formats include a header that describes the
-        included audio content. You can request recognition for ``WAV`` files that
-        contain either ``LINEAR16`` or ``MULAW`` encoded audio.
-        If you send ``FLAC`` or ``WAV`` audio file format in
-        your request, you do not need to specify an ``AudioEncoding``; the audio
-        encoding format is determined from the file header. If you specify
-        an ``AudioEncoding`` when you send  send ``FLAC`` or ``WAV`` audio, the
+        For best results, the audio source should be captured and transmitted
+        using a lossless encoding (``FLAC`` or ``LINEAR16``). The accuracy of
+        the speech recognition can be reduced if lossy codecs are used to
+        capture or transmit audio, particularly if background noise is present.
+        Lossy codecs include ``MULAW``, ``AMR``, ``AMR_WB``, ``OGG_OPUS``, and
+        ``SPEEX_WITH_HEADER_BYTE``.
+
+        The ``FLAC`` and ``WAV`` audio file formats include a header that
+        describes the included audio content. You can request recognition for
+        ``WAV`` files that contain either ``LINEAR16`` or ``MULAW`` encoded
+        audio. If you send ``FLAC`` or ``WAV`` audio file format in your
+        request, you do not need to specify an ``AudioEncoding``; the audio
+        encoding format is determined from the file header. If you specify an
+        ``AudioEncoding`` when you send send ``FLAC`` or ``WAV`` audio, the
         encoding configuration must match the encoding described in the audio
         header; otherwise the request returns an
         ``google.rpc.Code.INVALID_ARGUMENT`` error code.
 
         Attributes:
           ENCODING_UNSPECIFIED (int): Not specified.
           LINEAR16 (int): Uncompressed 16-bit signed little-endian samples (Linear PCM).
-          FLAC (int): ``FLAC`` (Free Lossless Audio
-          Codec) is the recommended encoding because it is
-          lossless--therefore recognition is not compromised--and
-          requires only about half the bandwidth of ``LINEAR16``. ``FLAC`` stream
-          encoding supports 16-bit and 24-bit samples, however, not all fields in
+          FLAC (int): ``FLAC`` (Free Lossless Audio Codec) is the recommended encoding because
+          it is lossless--therefore recognition is not compromised--and requires
+          only about half the bandwidth of ``LINEAR16``. ``FLAC`` stream encoding
+          supports 16-bit and 24-bit samples, however, not all fields in
           ``STREAMINFO`` are supported.
           MULAW (int): 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
-          AMR (int): Adaptive Multi-Rate Narrowband codec. ``sample_rate_hertz`` must be 8000.
+          AMR (int): Adaptive Multi-Rate Narrowband codec. ``sample_rate_hertz`` must be
+          8000.
           AMR_WB (int): Adaptive Multi-Rate Wideband codec. ``sample_rate_hertz`` must be 16000.
           OGG_OPUS (int): Opus encoded audio frames in Ogg container
-          (`OggOpus <https://wiki.xiph.org/OggOpus>`_).
-          ``sample_rate_hertz`` must be one of 8000, 12000, 16000, 24000, or 48000.
+          (`OggOpus <https://wiki.xiph.org/OggOpus>`__). ``sample_rate_hertz``
+          must be one of 8000, 12000, 16000, 24000, or 48000.
           SPEEX_WITH_HEADER_BYTE (int): Although the use of lossy encodings is not recommended, if a very low
           bitrate encoding is required, ``OGG_OPUS`` is highly preferred over
-          Speex encoding. The `Speex <https://speex.org/>`_  encoding supported by
+          Speex encoding. The `Speex <https://speex.org/>`__ encoding supported by
           Cloud Speech API has a header byte in each block, as in MIME type
-          ``audio/x-speex-with-header-byte``.
-          It is a variant of the RTP Speex encoding defined in
-          `RFC 5574 <https://tools.ietf.org/html/rfc5574>`_.
+          ``audio/x-speex-with-header-byte``. It is a variant of the RTP Speex
+          encoding defined in `RFC 5574 <https://tools.ietf.org/html/rfc5574>`__.
           The stream is a sequence of blocks, one block per RTP packet. Each block
-          starts with a byte containing the length of the block, in bytes, followed
-          by one or more frames of Speex data, padded to an integral number of
-          bytes (octets) as specified in RFC 5574. In other words, each RTP header
-          is replaced with a single byte containing the block length. Only Speex
-          wideband is supported. ``sample_rate_hertz`` must be 16000.
+          starts with a byte containing the length of the block, in bytes,
+          followed by one or more frames of Speex data, padded to an integral
+          number of bytes (octets) as specified in RFC 5574. In other words, each
+          RTP header is replaced with a single byte containing the block length.
+          Only Speex wideband is supported. ``sample_rate_hertz`` must be 16000.
         """
         ENCODING_UNSPECIFIED = 0
         LINEAR16 = 1
@@ -91,9 +91,9 @@ class InteractionType(enum.IntEnum):
           INTERACTION_TYPE_UNSPECIFIED (int): Use case is either unknown or is something other than one of the other
           values below.
           DISCUSSION (int): Multiple people in a conversation or discussion. For example in a
-          meeting with two or more people actively participating. Typically
-          all the primary people speaking would be in the same room (if not,
-          see PHONE_CALL)
+          meeting with two or more people actively participating. Typically all
+          the primary people speaking would be in the same room (if not, see
+          PHONE\_CALL)
           PRESENTATION (int): One or more persons lecturing or presenting to others, mostly
           uninterrupted.
           PHONE_CALL (int): A phone-call or video-conference in which two or more people, who are
@@ -178,9 +178,10 @@ class SpeechEventType(enum.IntEnum):
           speech utterance and expects no additional speech. Therefore, the server
           will not process additional audio (although it may subsequently return
           additional results). The client should stop sending additional audio
-          data, half-close the gRPC connection, and wait for any additional results
-          until the server closes the gRPC connection. This event is only sent if
-          ``single_utterance`` was set to ``true``, and is not used otherwise.
+          data, half-close the gRPC connection, and wait for any additional
+          results until the server closes the gRPC connection. This event is only
+          sent if ``single_utterance`` was set to ``true``, and is not used
+          otherwise.
         """
         SPEECH_EVENT_UNSPECIFIED = 0
         END_OF_SINGLE_UTTERANCE = 1