google-cloud-speech 0.34.1 → 0.35.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 363ea2b2a855f3a5721f14eaba4ebaea0c474912996d8777327a5593d58fb25a
-  data.tar.gz: 70445356ae04fe3a805efc76269d17269275d0ae4bc0e19ecc5915a63a2a5abe
+  metadata.gz: 5a486e59964640a724d7a70449004707ce610868a9d6776783758b8cefe1d01b
+  data.tar.gz: 0db54dd44e394919bc4f20d41f0570d52c8f543a136762e34700ef7daed98730
 SHA512:
-  metadata.gz: e9203cea2fc78d9d8cf7dd3d98ecad2e34c9e8e55755920171312221f63c27aca05dc7958260420804c51093ae928d8a070af33286fb117defdc6d0d0094c847
-  data.tar.gz: 2fc1a2c2bd6dfa40ab570d3c9447f02414134640a5ed6364d54285254f070e8d65e0af10fc4d8775583361c0e1e4d296a08e6e1d8f2f41dbcefb04d7d312bb69
+  metadata.gz: 56f72325d2e5420551029a13e2a1d7fd20a5eba658e3fa84998c5fc413cea15b87ea718839c309d7b6d545ba31b8f5ebdb548f0e475fe53a3bc798c0a716adf6
+  data.tar.gz: cab1730447f4ffc096e06c35d8d71b4b018a20ffc78414db896af76fb4290b41122174874d0a1b508f00609db8d3275c473c0de36c3d43c32bff598fddc1b269

data/lib/google/cloud/speech/v1/cloud_speech_pb.rb

@@ -6,9 +6,7 @@ require 'google/protobuf'
 
 require 'google/api/annotations_pb'
 require 'google/longrunning/operations_pb'
-require 'google/protobuf/any_pb'
 require 'google/protobuf/duration_pb'
-require 'google/protobuf/empty_pb'
 require 'google/protobuf/timestamp_pb'
 require 'google/rpc/status_pb'
 Google::Protobuf::DescriptorPool.generated_pool.build do
@@ -42,6 +40,7 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
     repeated :speech_contexts, :message, 6, "google.cloud.speech.v1.SpeechContext"
     optional :enable_word_time_offsets, :bool, 8
     optional :enable_automatic_punctuation, :bool, 11
+    optional :metadata, :message, 9, "google.cloud.speech.v1.RecognitionMetadata"
     optional :model, :string, 13
     optional :use_enhanced, :bool, 14
   end
@@ -55,6 +54,47 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
     value :OGG_OPUS, 6
     value :SPEEX_WITH_HEADER_BYTE, 7
   end
+  add_message "google.cloud.speech.v1.RecognitionMetadata" do
+    optional :interaction_type, :enum, 1, "google.cloud.speech.v1.RecognitionMetadata.InteractionType"
+    optional :industry_naics_code_of_audio, :uint32, 3
+    optional :microphone_distance, :enum, 4, "google.cloud.speech.v1.RecognitionMetadata.MicrophoneDistance"
+    optional :original_media_type, :enum, 5, "google.cloud.speech.v1.RecognitionMetadata.OriginalMediaType"
+    optional :recording_device_type, :enum, 6, "google.cloud.speech.v1.RecognitionMetadata.RecordingDeviceType"
+    optional :recording_device_name, :string, 7
+    optional :original_mime_type, :string, 8
+    optional :audio_topic, :string, 10
+  end
+  add_enum "google.cloud.speech.v1.RecognitionMetadata.InteractionType" do
+    value :INTERACTION_TYPE_UNSPECIFIED, 0
+    value :DISCUSSION, 1
+    value :PRESENTATION, 2
+    value :PHONE_CALL, 3
+    value :VOICEMAIL, 4
+    value :PROFESSIONALLY_PRODUCED, 5
+    value :VOICE_SEARCH, 6
+    value :VOICE_COMMAND, 7
+    value :DICTATION, 8
+  end
+  add_enum "google.cloud.speech.v1.RecognitionMetadata.MicrophoneDistance" do
+    value :MICROPHONE_DISTANCE_UNSPECIFIED, 0
+    value :NEARFIELD, 1
+    value :MIDFIELD, 2
+    value :FARFIELD, 3
+  end
+  add_enum "google.cloud.speech.v1.RecognitionMetadata.OriginalMediaType" do
+    value :ORIGINAL_MEDIA_TYPE_UNSPECIFIED, 0
+    value :AUDIO, 1
+    value :VIDEO, 2
+  end
+  add_enum "google.cloud.speech.v1.RecognitionMetadata.RecordingDeviceType" do
+    value :RECORDING_DEVICE_TYPE_UNSPECIFIED, 0
+    value :SMARTPHONE, 1
+    value :PC, 2
+    value :PHONE_LINE, 3
+    value :VEHICLE, 4
+    value :OTHER_OUTDOOR_DEVICE, 5
+    value :OTHER_INDOOR_DEVICE, 6
+  end
   add_message "google.cloud.speech.v1.SpeechContext" do
     repeated :phrases, :string, 1
   end
@@ -88,7 +128,9 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
     repeated :alternatives, :message, 1, "google.cloud.speech.v1.SpeechRecognitionAlternative"
     optional :is_final, :bool, 2
     optional :stability, :float, 3
+    optional :result_end_time, :message, 4, "google.protobuf.Duration"
     optional :channel_tag, :int32, 5
+    optional :language_code, :string, 6
   end
   add_message "google.cloud.speech.v1.SpeechRecognitionResult" do
     repeated :alternatives, :message, 1, "google.cloud.speech.v1.SpeechRecognitionAlternative"
@@ -116,6 +158,11 @@ module Google
         StreamingRecognitionConfig = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.StreamingRecognitionConfig").msgclass
         RecognitionConfig = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionConfig").msgclass
         RecognitionConfig::AudioEncoding = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionConfig.AudioEncoding").enummodule
+        RecognitionMetadata = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionMetadata").msgclass
+        RecognitionMetadata::InteractionType = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionMetadata.InteractionType").enummodule
+        RecognitionMetadata::MicrophoneDistance = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionMetadata.MicrophoneDistance").enummodule
+        RecognitionMetadata::OriginalMediaType = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionMetadata.OriginalMediaType").enummodule
+        RecognitionMetadata::RecordingDeviceType = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionMetadata.RecordingDeviceType").enummodule
         SpeechContext = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.SpeechContext").msgclass
         RecognitionAudio = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognitionAudio").msgclass
         RecognizeResponse = Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.RecognizeResponse").msgclass

data/lib/google/cloud/speech/v1/doc/google/cloud/speech/v1/cloud_speech.rb

@@ -165,6 +165,9 @@ module Google
         #     Note: This is currently offered as an experimental service, complimentary
         #     to all users. In the future this may be exclusively available as a
         #     premium feature.
+        # @!attribute [rw] metadata
+        #   @return [Google::Cloud::Speech::V1::RecognitionMetadata]
+        #     *Optional* Metadata regarding this request.
         # @!attribute [rw] model
         #   @return [String]
         #     *Optional* Which model to select for the given request. Select the model
@@ -284,6 +287,133 @@ module Google
           end
         end
 
+        # Description of audio data to be recognized.
+        # @!attribute [rw] interaction_type
+        #   @return [Google::Cloud::Speech::V1::RecognitionMetadata::InteractionType]
+        #     The use case most closely describing the audio content to be recognized.
+        # @!attribute [rw] industry_naics_code_of_audio
+        #   @return [Integer]
+        #     The industry vertical to which this speech recognition request most
+        #     closely applies. This is most indicative of the topics contained
+        #     in the audio.  Use the 6-digit NAICS code to identify the industry
+        #     vertical - see https://www.naics.com/search/.
+        # @!attribute [rw] microphone_distance
+        #   @return [Google::Cloud::Speech::V1::RecognitionMetadata::MicrophoneDistance]
+        #     The audio type that most closely describes the audio being recognized.
+        # @!attribute [rw] original_media_type
+        #   @return [Google::Cloud::Speech::V1::RecognitionMetadata::OriginalMediaType]
+        #     The original media the speech was recorded on.
+        # @!attribute [rw] recording_device_type
+        #   @return [Google::Cloud::Speech::V1::RecognitionMetadata::RecordingDeviceType]
+        #     The type of device the speech was recorded with.
+        # @!attribute [rw] recording_device_name
+        #   @return [String]
+        #     The device used to make the recording.  Examples 'Nexus 5X' or
+        #     'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
+        #     'Cardioid Microphone'.
+        # @!attribute [rw] original_mime_type
+        #   @return [String]
+        #     Mime type of the original audio file.  For example `audio/m4a`,
+        #     `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.
+        #     A list of possible audio mime types is maintained at
+        #     http://www.iana.org/assignments/media-types/media-types.xhtml#audio
+        # @!attribute [rw] audio_topic
+        #   @return [String]
+        #     Description of the content. Eg. "Recordings of federal supreme court
+        #     hearings from 2012".
+        class RecognitionMetadata
+          # Use case categories that the audio recognition request can be described
+          # by.
+          module InteractionType
+            # Use case is either unknown or is something other than one of the other
+            # values below.
+            INTERACTION_TYPE_UNSPECIFIED = 0
+
+            # 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)
+            DISCUSSION = 1
+
+            # One or more persons lecturing or presenting to others, mostly
+            # uninterrupted.
+            PRESENTATION = 2
+
+            # A phone-call or video-conference in which two or more people, who are
+            # not in the same room, are actively participating.
+            PHONE_CALL = 3
+
+            # A recorded message intended for another person to listen to.
+            VOICEMAIL = 4
+
+            # Professionally produced audio (eg. TV Show, Podcast).
+            PROFESSIONALLY_PRODUCED = 5
+
+            # Transcribe spoken questions and queries into text.
+            VOICE_SEARCH = 6
+
+            # Transcribe voice commands, such as for controlling a device.
+            VOICE_COMMAND = 7
+
+            # Transcribe speech to text to create a written document, such as a
+            # text-message, email or report.
+            DICTATION = 8
+          end
+
+          # Enumerates the types of capture settings describing an audio file.
+          module MicrophoneDistance
+            # Audio type is not known.
+            MICROPHONE_DISTANCE_UNSPECIFIED = 0
+
+            # The audio was captured from a closely placed microphone. Eg. phone,
+            # dictaphone, or handheld microphone. Generally if there speaker is within
+            # 1 meter of the microphone.
+            NEARFIELD = 1
+
+            # The speaker if within 3 meters of the microphone.
+            MIDFIELD = 2
+
+            # The speaker is more than 3 meters away from the microphone.
+            FARFIELD = 3
+          end
+
+          # The original media the speech was recorded on.
+          module OriginalMediaType
+            # Unknown original media type.
+            ORIGINAL_MEDIA_TYPE_UNSPECIFIED = 0
+
+            # The speech data is an audio recording.
+            AUDIO = 1
+
+            # The speech data originally recorded on a video.
+            VIDEO = 2
+          end
+
+          # The type of device the speech was recorded with.
+          module RecordingDeviceType
+            # The recording device is unknown.
+            RECORDING_DEVICE_TYPE_UNSPECIFIED = 0
+
+            # Speech was recorded on a smartphone.
+            SMARTPHONE = 1
+
+            # Speech was recorded using a personal computer or tablet.
+            PC = 2
+
+            # Speech was recorded over a phone line.
+            PHONE_LINE = 3
+
+            # Speech was recorded in a vehicle.
+            VEHICLE = 4
+
+            # Speech was recorded outdoors.
+            OTHER_OUTDOOR_DEVICE = 5
+
+            # Speech was recorded indoors.
+            OTHER_INDOOR_DEVICE = 6
+          end
+        end
+
         # Provides "hints" to the speech recognizer to favor specific words and phrases
         # in the results.
         # @!attribute [rw] phrases
@@ -453,11 +583,21 @@ module Google
         #     (completely unstable) to 1.0 (completely stable).
         #     This field is only provided for interim results (`is_final=false`).
         #     The default of 0.0 is a sentinel value indicating `stability` was not set.
+        # @!attribute [rw] result_end_time
+        #   @return [Google::Protobuf::Duration]
+        #     Output only. Time offset of the end of this result relative to the
+        #     beginning of the audio.
         # @!attribute [rw] channel_tag
         #   @return [Integer]
         #     For multi-channel audio, this is the channel number corresponding to the
         #     recognized result for the audio from that channel.
         #     For audio_channel_count = N, its output values can range from '1' to 'N'.
+        # @!attribute [rw] language_code
+        #   @return [String]
+        #     Output only. The
+        #     [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
+        #     language in this result. This language code was detected to have the most
+        #     likelihood of being spoken in the audio.
         class StreamingRecognitionResult; end
 
         # A speech recognition result corresponding to a portion of the audio.

data/lib/google/cloud/speech/v1/speech_client.rb

@@ -29,6 +29,7 @@ require "google/longrunning/operations_client"
 
 require "google/cloud/speech/v1/cloud_speech_pb"
 require "google/cloud/speech/v1/credentials"
+require "google/cloud/speech/version"
 
 module Google
   module Cloud
@@ -136,7 +137,7 @@ module Google
               updater_proc = credentials.updater_proc
             end
 
-            package_version = Gem.loaded_specs['google-cloud-speech'].version.version
+            package_version = Google::Cloud::Speech::VERSION
 
             google_api_client = "gl-ruby/#{RUBY_VERSION}"
             google_api_client << " #{lib_name}/#{lib_version}" if lib_name

data/lib/google/cloud/speech/v1p1beta1/cloud_speech_pb.rb

@@ -59,6 +59,7 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
     value :AMR_WB, 5
     value :OGG_OPUS, 6
     value :SPEEX_WITH_HEADER_BYTE, 7
+    value :MP3, 8
   end
   add_message "google.cloud.speech.v1p1beta1.RecognitionMetadata" do
     optional :interaction_type, :enum, 1, "google.cloud.speech.v1p1beta1.RecognitionMetadata.InteractionType"
@@ -104,6 +105,7 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
   end
   add_message "google.cloud.speech.v1p1beta1.SpeechContext" do
     repeated :phrases, :string, 1
+    optional :boost, :float, 4
   end
   add_message "google.cloud.speech.v1p1beta1.RecognitionAudio" do
     oneof :audio_source do

data/lib/google/cloud/speech/v1p1beta1/doc/google/cloud/speech/v1p1beta1/cloud_speech.rb

@@ -321,6 +321,11 @@ module Google
             # is replaced with a single byte containing the block length. Only Speex
             # wideband is supported. `sample_rate_hertz` must be 16000.
             SPEEX_WITH_HEADER_BYTE = 7
+
+            # MP3 audio. Support all standard MP3 bitrates (which range from 32-320
+            # kbps). When using this encoding, `sample_rate_hertz` can be optionally
+            # unset if not known.
+            MP3 = 8
           end
         end
 
@@ -465,6 +470,22 @@ module Google
         #     specific commands are typically spoken by the user. This can also be used
         #     to add additional words to the vocabulary of the recognizer. See
         #     [usage limits](https://cloud.google.com/speech-to-text/quotas#content).
+        #
+        #     List items can also be set to classes for groups of words that represent
+        #     common concepts that occur in natural language. For example, rather than
+        #     providing phrase hints for every month of the year, using the $MONTH class
+        #     improves the likelihood of correctly transcribing audio that includes
+        #     months.
+        # @!attribute [rw] boost
+        #   @return [Float]
+        #     Hint Boost. Positive value will increase the probability that a specific
+        #     phrase will be recognized over other similar sounding phrases. The higher
+        #     the boost, the higher the chance of false positive recognition as well.
+        #     Negative boost values would correspond to anti-biasing. Anti-biasing is not
+        #     enabled, so negative boost will simply be ignored. Though `boost` can
+        #     accept a wide range of positive values, most use cases are best served with
+        #     values between 0 and 20. We recommend using a binary search approach to
+        #     finding the optimal value for your use case.
         class SpeechContext; end
 
         # Contains audio data in the encoding specified in the `RecognitionConfig`.

data/lib/google/cloud/speech/v1p1beta1/speech_client.rb

@@ -29,6 +29,7 @@ require "google/longrunning/operations_client"
 
 require "google/cloud/speech/v1p1beta1/cloud_speech_pb"
 require "google/cloud/speech/v1p1beta1/credentials"
+require "google/cloud/speech/version"
 
 module Google
   module Cloud
@@ -136,7 +137,7 @@ module Google
               updater_proc = credentials.updater_proc
             end
 
-            package_version = Gem.loaded_specs['google-cloud-speech'].version.version
+            package_version = Google::Cloud::Speech::VERSION
 
             google_api_client = "gl-ruby/#{RUBY_VERSION}"
             google_api_client << " #{lib_name}/#{lib_version}" if lib_name

data/lib/google/cloud/speech/version.rb

@@ -0,0 +1,22 @@
+# Copyright 2019 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+module Google
+  module Cloud
+    module Speech
+      VERSION = "0.35.0".freeze
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: google-cloud-speech
 version: !ruby/object:Gem::Version
-  version: 0.34.1
+  version: 0.35.0
 platform: ruby
 authors:
 - Google LLC
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-04-30 00:00:00.000000000 Z
+date: 2019-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: google-gax
@@ -131,6 +131,7 @@ files:
 - lib/google/cloud/speech/v1p1beta1/speech_client.rb
 - lib/google/cloud/speech/v1p1beta1/speech_client_config.json
 - lib/google/cloud/speech/v1p1beta1/stream.rb
+- lib/google/cloud/speech/version.rb
 homepage: https://github.com/googleapis/googleapis
 licenses:
 - Apache-2.0