google-cloud-speech-v2 0.1.0 → 0.3.0

data/proto_docs/google/cloud/speech/v2/cloud_speech.rb

@@ -275,22 +275,44 @@ module Google
         #       When using this model, the service will stop transcribing audio after the
         #       first utterance is detected and completed.
         #
-        #     When using this model,
-        #     {::Google::Cloud::Speech::V2::RecognitionFeatures::MultiChannelMode::SEPARATE_RECOGNITION_PER_CHANNEL SEPARATE_RECOGNITION_PER_CHANNEL}
-        #     is not supported; multi-channel audio is accepted, but only the first
-        #     channel will be processed and transcribed.
+        #       When using this model,
+        #       {::Google::Cloud::Speech::V2::RecognitionFeatures::MultiChannelMode::SEPARATE_RECOGNITION_PER_CHANNEL SEPARATE_RECOGNITION_PER_CHANNEL}
+        #       is not supported; multi-channel audio is accepted, but only the first
+        #       channel will be processed and transcribed.
+        #
+        #     - `telephony`
+        #
+        #       Best for audio that originated from a phone call (typically recorded at
+        #       an 8khz sampling rate).
+        #
+        #     - `medical_conversation`
+        #
+        #       For conversations between a medical provider—for example, a doctor or
+        #       nurse—and a patient. Use this model when both a provider and a patient
+        #       are speaking. Words uttered by each speaker are automatically detected
+        #       and labeled in the returned transcript.
+        #
+        #       For supported features please see [medical models
+        #       documentation](https://cloud.google.com/speech-to-text/docs/medical-models).
+        #
+        #     - `medical_dictation`
+        #
+        #       For dictated notes spoken by a single medical provider—for example, a
+        #       doctor dictating notes about a patient's blood test results.
+        #
+        #       For supported features please see [medical models
+        #       documentation](https://cloud.google.com/speech-to-text/docs/medical-models).
+        #
+        #     - `usm`
+        #
+        #       The next generation of Speech-to-Text models from Google.
         # @!attribute [rw] language_codes
         #   @return [::Array<::String>]
         #     Required. The language of the supplied audio as a
         #     [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
         #
-        #     Supported languages:
-        #
-        #     - `en-US`
-        #
-        #     - `en-GB`
-        #
-        #     - `fr-FR`
+        #     Supported languages for each model are listed at:
+        #     https://cloud.google.com/speech-to-text/docs/languages
         #
         #     If additional languages are provided, recognition result will contain
         #     recognition in the most likely language detected. The recognition result
@@ -373,14 +395,23 @@ module Google
 
         # Automatically detected decoding parameters.
         # Supported for the following encodings:
+        #
         # * WAV_LINEAR16: 16-bit signed little-endian PCM samples in a WAV container.
+        #
         # * WAV_MULAW: 8-bit companded mulaw samples in a WAV container.
+        #
         # * WAV_ALAW: 8-bit companded alaw samples in a WAV container.
+        #
         # * RFC4867_5_AMR: AMR frames with an rfc4867.5 header.
+        #
         # * RFC4867_5_AMRWB: AMR-WB frames with an rfc4867.5 header.
+        #
         # * FLAC: FLAC frames in the "native FLAC" container format.
+        #
         # * MP3: MPEG audio frames with optional (ignored) ID3 metadata.
+        #
         # * OGG_OPUS: Opus audio frames in an Ogg container.
+        #
         # * WEBM_OPUS: Opus audio frames in a WebM container.
         class AutoDetectDecodingConfig
           include ::Google::Protobuf::MessageExts
@@ -398,16 +429,24 @@ module Google
         #     sampling rate of the audio source to 16000 Hz. If that's not possible, use
         #     the native sample rate of the audio source (instead of re-sampling).
         #     Supported for the following encodings:
+        #
         #     * LINEAR16: Headerless 16-bit signed little-endian PCM samples.
+        #
         #     * MULAW: Headerless 8-bit companded mulaw samples.
+        #
         #     * ALAW: Headerless 8-bit companded alaw samples.
         # @!attribute [rw] audio_channel_count
         #   @return [::Integer]
         #     Number of channels present in the audio data sent for recognition.
         #     Supported for the following encodings:
+        #
         #     * LINEAR16: Headerless 16-bit signed little-endian PCM samples.
+        #
         #     * MULAW: Headerless 8-bit companded mulaw samples.
+        #
         #     * ALAW: Headerless 8-bit companded alaw samples.
+        #
+        #     The maximum allowed value is 8.
         class ExplicitDecodingConfig
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -433,7 +472,7 @@ module Google
         #   @return [::Integer]
         #     Required. Minimum number of speakers in the conversation. This range gives
         #     you more flexibility by allowing the system to automatically determine the
-        #     correct number of speakers. If not set, the default value is 2.
+        #     correct number of speakers.
         #
         #     To fix the number of speakers detected in the audio, set
         #     `min_speaker_count` = `max_speaker_count`.
@@ -521,28 +560,28 @@ module Google
         end
 
         # Provides "hints" to the speech recognizer to favor specific words and phrases
-        # in the results. Phrase sets can be specified as an inline resource, or a
-        # reference to an existing phrase set resource.
+        # in the results. PhraseSets can be specified as an inline resource, or a
+        # reference to an existing PhraseSet resource.
         # @!attribute [rw] phrase_sets
         #   @return [::Array<::Google::Cloud::Speech::V2::SpeechAdaptation::AdaptationPhraseSet>]
-        #     A list of inline or referenced phrase sets.
+        #     A list of inline or referenced PhraseSets.
         # @!attribute [rw] custom_classes
         #   @return [::Array<::Google::Cloud::Speech::V2::CustomClass>]
-        #     A list of inline custom classes. Existing custom class resources can be
-        #     referenced directly in a phrase set.
+        #     A list of inline CustomClasses. Existing CustomClass resources can be
+        #     referenced directly in a PhraseSet.
         class SpeechAdaptation
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
 
-          # A biasing phrase set, which can be either a string referencing the name of
-          # an existing phrase set resource, or an inline definition of a phrase set.
+          # A biasing PhraseSet, which can be either a string referencing the name of
+          # an existing PhraseSets resource, or an inline definition of a PhraseSet.
           # @!attribute [rw] phrase_set
           #   @return [::String]
-          #     The name of an existing phrase set resource. The user must have read
+          #     The name of an existing PhraseSet resource. The user must have read
           #     access to the resource and it must not be deleted.
           # @!attribute [rw] inline_phrase_set
           #   @return [::Google::Cloud::Speech::V2::PhraseSet]
-          #     An inline defined phrase set.
+          #     An inline defined PhraseSet.
           class AdaptationPhraseSet
             include ::Google::Protobuf::MessageExts
             extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -651,9 +690,9 @@ module Google
         # @!attribute [rw] words
         #   @return [::Array<::Google::Cloud::Speech::V2::WordInfo>]
         #     A list of word-specific information for each recognized word.
-        #     When
-        #     [enable_speaker_diarization][google.cloud.speech.v2.SpeakerDiarizationConfig.enable_speaker_diarization]
-        #     is true, you will see all the words from the beginning of the audio.
+        #     When the
+        #     {::Google::Cloud::Speech::V2::SpeakerDiarizationConfig SpeakerDiarizationConfig}
+        #     is set, you will see all the words from the beginning of the audio.
         class SpeechRecognitionAlternative
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -694,8 +733,8 @@ module Google
         #     A distinct label is assigned for every speaker within the audio. This field
         #     specifies which one of those speakers was detected to have spoken this
         #     word. `speaker_label` is set if
-        #     [enable_speaker_diarization][google.cloud.speech.v2.SpeakerDiarizationConfig.enable_speaker_diarization]
-        #     is `true` and only in the top alternative.
+        #     {::Google::Cloud::Speech::V2::SpeakerDiarizationConfig SpeakerDiarizationConfig}
+        #     is given and only in the top alternative.
         class WordInfo
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -795,9 +834,9 @@ module Google
         #     of the recognizer during this recognition request. If no mask is provided,
         #     all non-default valued fields in
         #     {::Google::Cloud::Speech::V2::StreamingRecognitionConfig#config config} override
-        #     the values in the recognizer for this recognition request. If a mask is
+        #     the values in the Recognizer for this recognition request. If a mask is
         #     provided, only the fields listed in the mask override the config in the
-        #     recognizer for this recognition request. If a wildcard (`*`) is provided,
+        #     Recognizer for this recognition request. If a wildcard (`*`) is provided,
         #     {::Google::Cloud::Speech::V2::StreamingRecognitionConfig#config config}
         #     completely overrides and replaces the config in the recognizer for this
         #     recognition request.
@@ -841,6 +880,7 @@ module Google
         # @!attribute [rw] audio
         #   @return [::String]
         #     Inline audio bytes to be Recognized.
+        #     Maximum size for this field is 15 KB per request.
         class StreamingRecognizeRequest
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -878,17 +918,57 @@ module Google
         # @!attribute [rw] files
         #   @return [::Array<::Google::Cloud::Speech::V2::BatchRecognizeFileMetadata>]
         #     Audio files with file metadata for ASR.
+        #     The maximum number of files allowed to be specified is 5.
+        # @!attribute [rw] recognition_output_config
+        #   @return [::Google::Cloud::Speech::V2::RecognitionOutputConfig]
+        #     Configuration options for where to output the transcripts of each file.
         class BatchRecognizeRequest
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
         end
 
+        # Output configurations for Cloud Storage.
+        # @!attribute [rw] uri
+        #   @return [::String]
+        #     The Cloud Storage URI prefix with which recognition results will be
+        #     written.
+        class GcsOutputConfig
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Output configurations for inline response.
+        class InlineOutputConfig
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Configuration options for the output(s) of recognition.
+        # @!attribute [rw] gcs_output_config
+        #   @return [::Google::Cloud::Speech::V2::GcsOutputConfig]
+        #     If this message is populated, recognition results are written to the
+        #     provided Google Cloud Storage URI.
+        # @!attribute [rw] inline_response_config
+        #   @return [::Google::Cloud::Speech::V2::InlineOutputConfig]
+        #     If this message is populated, recognition results are provided in the
+        #     {::Google::Cloud::Speech::V2::BatchRecognizeResponse BatchRecognizeResponse}
+        #     message of the Operation when completed. This is only supported when
+        #     calling {::Google::Cloud::Speech::V2::Speech::Client#batch_recognize BatchRecognize}
+        #     with just one audio file.
+        class RecognitionOutputConfig
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
         # Response message for
         # {::Google::Cloud::Speech::V2::Speech::Client#batch_recognize BatchRecognize} that is
         # packaged into a longrunning {::Google::Longrunning::Operation Operation}.
         # @!attribute [rw] results
         #   @return [::Google::Protobuf::Map{::String => ::Google::Cloud::Speech::V2::BatchRecognizeFileResult}]
         #     Map from filename to the final result for that file.
+        # @!attribute [rw] total_billed_duration
+        #   @return [::Google::Protobuf::Duration]
+        #     When available, billed audio seconds for the corresponding request.
         class BatchRecognizeResponse
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -903,13 +983,36 @@ module Google
           end
         end
 
+        # Output type for Cloud Storage of BatchRecognize transcripts. Though this
+        # proto isn't returned in this API anywhere, the Cloud Storage transcripts will
+        # be this proto serialized and should be parsed as such.
+        # @!attribute [rw] results
+        #   @return [::Array<::Google::Cloud::Speech::V2::SpeechRecognitionResult>]
+        #     Sequential list of transcription results corresponding to sequential
+        #     portions of audio.
+        # @!attribute [rw] metadata
+        #   @return [::Google::Cloud::Speech::V2::RecognitionResponseMetadata]
+        #     Metadata about the recognition.
+        class BatchRecognizeResults
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
         # Final results for a single file.
         # @!attribute [rw] uri
         #   @return [::String]
-        #     The GCS URI to which recognition results were written.
+        #     The Cloud Storage URI to which recognition results were written.
         # @!attribute [rw] error
         #   @return [::Google::Rpc::Status]
         #     Error if one was encountered.
+        # @!attribute [rw] metadata
+        #   @return [::Google::Cloud::Speech::V2::RecognitionResponseMetadata]
+        # @!attribute [rw] transcript
+        #   @return [::Google::Cloud::Speech::V2::BatchRecognizeResults]
+        #     The transcript for the audio file. This is populated only when
+        #     {::Google::Cloud::Speech::V2::InlineOutputConfig InlineOutputConfig} is set in
+        #     the
+        #     [RecognitionOutputConfig][[google.cloud.speech.v2.RecognitionOutputConfig].
         class BatchRecognizeFileResult
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -925,7 +1028,7 @@ module Google
         #     Error if one was encountered.
         # @!attribute [rw] uri
         #   @return [::String]
-        #     The GCS URI to which recognition results will be written.
+        #     The Cloud Storage URI to which recognition results will be written.
         class BatchRecognizeTranscriptionMetadata
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -1290,7 +1393,8 @@ module Google
         #     phrase will be recognized over other similar sounding phrases. The higher
         #     the boost, the higher the chance of false positive recognition as well.
         #     Valid `boost` values are between 0 (exclusive) and 20. We recommend using a
-        #     binary search approach to finding the optimal value for your use case.
+        #     binary search approach to finding the optimal value for your use case as
+        #     well as adding phrases both with and without boost to your requests.
         # @!attribute [rw] display_name
         #   @return [::String]
         #     User-settable, human-readable name for the PhraseSet. Must be 63
@@ -1358,11 +1462,11 @@ module Google
           #     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. Speech recognition
-          #     will skip PhraseSets with a boost value of 0.
+          #     enabled, so negative boost values will return an error. Boost values must
+          #     be between 0 and 20. Any values outside that range will return an error.
+          #     We recommend using a binary search approach to finding the optimal value
+          #     for your use case as well as adding phrases both with and without boost
+          #     to your requests.
           class Phrase
             include ::Google::Protobuf::MessageExts
             extend ::Google::Protobuf::MessageExts::ClassMethods

data/proto_docs/google/rpc/status.rb

@@ -28,12 +28,14 @@ module Google
     # [API Design Guide](https://cloud.google.com/apis/design/errors).
     # @!attribute [rw] code
     #   @return [::Integer]
-    #     The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code].
+    #     The status code, which should be an enum value of
+    #     [google.rpc.Code][google.rpc.Code].
     # @!attribute [rw] message
     #   @return [::String]
     #     A developer-facing error message, which should be in English. Any
     #     user-facing error message should be localized and sent in the
-    #     {::Google::Rpc::Status#details google.rpc.Status.details} field, or localized by the client.
+    #     {::Google::Rpc::Status#details google.rpc.Status.details} field, or localized
+    #     by the client.
     # @!attribute [rw] details
     #   @return [::Array<::Google::Protobuf::Any>]
     #     A list of messages that carry the error details.  There is a common set of

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: google-cloud-speech-v2
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Google LLC
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-10-03 00:00:00.000000000 Z
+date: 2023-03-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: gapic-common
@@ -16,7 +16,7 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0.12'
+        version: 0.18.0
     - - "<"
       - !ruby/object:Gem::Version
         version: 2.a
@@ -26,7 +26,7 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0.12'
+        version: 0.18.0
     - - "<"
       - !ruby/object:Gem::Version
         version: 2.a
@@ -44,20 +44,40 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: google-cloud-location
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.4'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: 2.a
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.4'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: 2.a
 - !ruby/object:Gem::Dependency
   name: google-style
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.26.1
+        version: 1.26.3
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.26.1
+        version: 1.26.3
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -175,16 +195,24 @@ files:
 - README.md
 - lib/google-cloud-speech-v2.rb
 - lib/google/cloud/speech/v2.rb
+- lib/google/cloud/speech/v2/bindings_override.rb
 - lib/google/cloud/speech/v2/cloud_speech_pb.rb
 - lib/google/cloud/speech/v2/cloud_speech_services_pb.rb
+- lib/google/cloud/speech/v2/rest.rb
 - lib/google/cloud/speech/v2/speech.rb
 - lib/google/cloud/speech/v2/speech/client.rb
 - lib/google/cloud/speech/v2/speech/credentials.rb
 - lib/google/cloud/speech/v2/speech/operations.rb
 - lib/google/cloud/speech/v2/speech/paths.rb
+- lib/google/cloud/speech/v2/speech/rest.rb
+- lib/google/cloud/speech/v2/speech/rest/client.rb
+- lib/google/cloud/speech/v2/speech/rest/operations.rb
+- lib/google/cloud/speech/v2/speech/rest/service_stub.rb
 - lib/google/cloud/speech/v2/version.rb
 - proto_docs/README.md
+- proto_docs/google/api/client.rb
 - proto_docs/google/api/field_behavior.rb
+- proto_docs/google/api/launch_stage.rb
 - proto_docs/google/api/resource.rb
 - proto_docs/google/cloud/speech/v2/cloud_speech.rb
 - proto_docs/google/longrunning/operations.rb
@@ -213,8 +241,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.14
+rubygems_version: 3.4.2
 signing_key: 
 specification_version: 4
-summary: API Client library for the Cloud Speech-to-Text V2 API
+summary: Converts audio to text by applying powerful neural network models.
 test_files: []