feat: Added SuggestConversationSummary RPC (#978)

* feat: Added SuggestConversationSummary RPC docs: updated go library package PiperOrigin-RevId: 501862436 Source-Link: googleapis/googleapis@155e0f4 Source-Link: googleapis/googleapis-gen@3051f61 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiMzA1MWY2MTdhOTkxYzI3NGM4OGQyNzA2NGU4MDMwOTVlNGVmOWQzOSJ9 feat: Added ABNF Grammars field in Speech Adaptation * Added a new field to Speech Adaptation to specify ABNF grammar definitions PiperOrigin-RevId: 499896786 Source-Link: googleapis/googleapis@ba57145 Source-Link: googleapis/googleapis-gen@f5d8be2 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZjVkOGJlMjkwNTYzMTFjMzBkZTkzMGZjMDk5YmFjY2ZiZDBlYWJlYiJ9 feat: Added new fields to facilitate debugging * Added new field to Speech response proto, to give more information to indicate whether, or not, Biasing was applied (eg. did Biasing application timed out). * Added request_id to Speech response protos. PiperOrigin-RevId: 493311906 Source-Link: googleapis/googleapis@c9b244b Source-Link: googleapis/googleapis-gen@d63ac84 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZDYzYWM4NDBkZWM4NTRlZTdhY2FiN2I1MmIxNWRlYWY4MTllYWUwNyJ9 chore: Enable requesting numeric enums in "transport=rest" responses for services supporting this (Java, Go, Python, PHP, TypeScript, C#, and Ruby), even if they do not yet turn on REST transport chore: disallow "transport=rest" for services where numeric enums are not confirmed to be supported (except in PHP and Java) PiperOrigin-RevId: 493113566 Source-Link: googleapis/googleapis@758f0d1 Source-Link: googleapis/googleapis-gen@78bd8f0 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiNzhiZDhmMDVlMTI3NjM2M2ViMTRlYWU3MGU5MWZlNGJjMjA3MDNhYiJ9 feat: Added new fields to facilitate debugging * Added new field to Speech response proto, to give more information to indicate whether, or not, Biasing was applied (eg. did Biasing application timed out). * Added request_id to Speech response protos. PiperOrigin-RevId: 492276727 Source-Link: googleapis/googleapis@4c25335 Source-Link: googleapis/googleapis-gen@f15b9ac Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZjE1YjlhY2E3YWMyYmQ0MGIyMGU2NzE1MTg4NzMyZDA4ZmM3ZmUyMSJ9 * feat: Added SuggestConversationSummary RPC docs: updated go library package PiperOrigin-RevId: 501862436 Source-Link: googleapis/googleapis@155e0f4 Source-Link: googleapis/googleapis-gen@3051f61 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiMzA1MWY2MTdhOTkxYzI3NGM4OGQyNzA2NGU4MDMwOTVlNGVmOWQzOSJ9 feat: Added ABNF Grammars field in Speech Adaptation * Added a new field to Speech Adaptation to specify ABNF grammar definitions PiperOrigin-RevId: 499896786 Source-Link: googleapis/googleapis@ba57145 Source-Link: googleapis/googleapis-gen@f5d8be2 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZjVkOGJlMjkwNTYzMTFjMzBkZTkzMGZjMDk5YmFjY2ZiZDBlYWJlYiJ9 feat: Added new fields to facilitate debugging * Added new field to Speech response proto, to give more information to indicate whether, or not, Biasing was applied (eg. did Biasing application timed out). * Added request_id to Speech response protos. PiperOrigin-RevId: 493311906 Source-Link: googleapis/googleapis@c9b244b Source-Link: googleapis/googleapis-gen@d63ac84 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZDYzYWM4NDBkZWM4NTRlZTdhY2FiN2I1MmIxNWRlYWY4MTllYWUwNyJ9 chore: Enable requesting numeric enums in "transport=rest" responses for services supporting this (Java, Go, Python, PHP, TypeScript, C#, and Ruby), even if they do not yet turn on REST transport chore: disallow "transport=rest" for services where numeric enums are not confirmed to be supported (except in PHP and Java) PiperOrigin-RevId: 493113566 Source-Link: googleapis/googleapis@758f0d1 Source-Link: googleapis/googleapis-gen@78bd8f0 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiNzhiZDhmMDVlMTI3NjM2M2ViMTRlYWU3MGU5MWZlNGJjMjA3MDNhYiJ9 feat: Added new fields to facilitate debugging * Added new field to Speech response proto, to give more information to indicate whether, or not, Biasing was applied (eg. did Biasing application timed out). * Added request_id to Speech response protos. PiperOrigin-RevId: 492276727 Source-Link: googleapis/googleapis@4c25335 Source-Link: googleapis/googleapis-gen@f15b9ac Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZjE1YjlhY2E3YWMyYmQ0MGIyMGU2NzE1MTg4NzMyZDA4ZmM3ZmUyMSJ9 * feat: Added SuggestConversationSummary RPC docs: updated go library package PiperOrigin-RevId: 501862436 Source-Link: googleapis/googleapis@155e0f4 Source-Link: googleapis/googleapis-gen@3051f61 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiMzA1MWY2MTdhOTkxYzI3NGM4OGQyNzA2NGU4MDMwOTVlNGVmOWQzOSJ9 feat: Added ABNF Grammars field in Speech Adaptation * Added a new field to Speech Adaptation to specify ABNF grammar definitions PiperOrigin-RevId: 499896786 Source-Link: googleapis/googleapis@ba57145 Source-Link: googleapis/googleapis-gen@f5d8be2 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZjVkOGJlMjkwNTYzMTFjMzBkZTkzMGZjMDk5YmFjY2ZiZDBlYWJlYiJ9 feat: Added new fields to facilitate debugging * Added new field to Speech response proto, to give more information to indicate whether, or not, Biasing was applied (eg. did Biasing application timed out). * Added request_id to Speech response protos. PiperOrigin-RevId: 493311906 Source-Link: googleapis/googleapis@c9b244b Source-Link: googleapis/googleapis-gen@d63ac84 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZDYzYWM4NDBkZWM4NTRlZTdhY2FiN2I1MmIxNWRlYWY4MTllYWUwNyJ9 chore: Enable requesting numeric enums in "transport=rest" responses for services supporting this (Java, Go, Python, PHP, TypeScript, C#, and Ruby), even if they do not yet turn on REST transport chore: disallow "transport=rest" for services where numeric enums are not confirmed to be supported (except in PHP and Java) PiperOrigin-RevId: 493113566 Source-Link: googleapis/googleapis@758f0d1 Source-Link: googleapis/googleapis-gen@78bd8f0 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiNzhiZDhmMDVlMTI3NjM2M2ViMTRlYWU3MGU5MWZlNGJjMjA3MDNhYiJ9 feat: Added new fields to facilitate debugging * Added new field to Speech response proto, to give more information to indicate whether, or not, Biasing was applied (eg. did Biasing application timed out). * Added request_id to Speech response protos. PiperOrigin-RevId: 492276727 Source-Link: googleapis/googleapis@4c25335 Source-Link: googleapis/googleapis-gen@f15b9ac Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiZjE1YjlhY2E3YWMyYmQ0MGIyMGU2NzE1MTg4NzMyZDA4ZmM3ZmUyMSJ9 * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
googleapis · Jan 20, 2023 · f1fc857 · f1fc857
1 parent 3b5363c
commit f1fc857
Show file tree

Hide file tree

Showing 73 changed files with 3,136 additions and 93 deletions.
diff --git a/.jsdoc.js b/.jsdoc.js
@@ -1,4 +1,4 @@
-// Copyright 2022 Google LLC
+// Copyright 2023 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -40,7 +40,7 @@ module.exports = {
     includePattern: '\\.js$'
   },
   templates: {
-    copyright: 'Copyright 2022 Google LLC',
+    copyright: 'Copyright 2023 Google LLC',
     includeDate: false,
     sourceFiles: false,
     systemName: '@google-cloud/speech',

diff --git a/protos/google/cloud/speech/v1/cloud_speech.proto b/protos/google/cloud/speech/v1/cloud_speech.proto
@@ -260,8 +260,7 @@ message RecognitionConfig {
 
   // The number of channels in the input audio data.
   // ONLY set this for MULTI-CHANNEL recognition.
-  // Valid values for LINEAR16 and FLAC are `1`-`8`.
-  // Valid values for OGG_OPUS are '1'-'254'.
+  // Valid values for LINEAR16, OGG_OPUS and FLAC are `1`-`8`.
   // Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
   // If `0` or omitted, defaults to one channel (mono).
   // Note: We only recognize the first channel by default.
@@ -652,6 +651,13 @@ message RecognizeResponse {
 
   // When available, billed audio seconds for the corresponding request.
   google.protobuf.Duration total_billed_time = 3;
+
+  // Provides information on adaptation behavior in response
+  SpeechAdaptationInfo speech_adaptation_info = 7;
+
+  // The ID associated with the request. This is a unique ID specific only to
+  // the given request.
+  int64 request_id = 8;
 }
 
 // The only message returned to the client by the `LongRunningRecognize` method.
@@ -672,6 +678,13 @@ message LongRunningRecognizeResponse {
 
   // If the transcript output fails this field contains the relevant error.
   google.rpc.Status output_error = 7;
+
+  // Provides information on speech adaptation behavior in response
+  SpeechAdaptationInfo speech_adaptation_info = 8;
+
+  // The ID associated with the request. This is a unique ID specific only to
+  // the given request.
+  int64 request_id = 9;
 }
 
 // Describes the progress of a long-running `LongRunningRecognize` call. It is
@@ -774,6 +787,13 @@ message StreamingRecognizeResponse {
   // When available, billed audio seconds for the stream.
   // Set only if this is the last response in the stream.
   google.protobuf.Duration total_billed_time = 5;
+
+  // Provides information on adaptation behavior in response
+  SpeechAdaptationInfo speech_adaptation_info = 9;
+
+  // The ID associated with the request. This is a unique ID specific only to
+  // the given request.
+  int64 request_id = 10;
 }
 
 // A streaming speech recognition result corresponding to a portion of the audio
@@ -897,3 +917,14 @@ message WordInfo {
   // top alternative.
   int32 speaker_tag = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
+
+// Information on speech adaptation use in results
+message SpeechAdaptationInfo {
+  // Whether there was a timeout when applying speech adaptation. If true,
+  // adaptation had no effect in the response transcript.
+  bool adaptation_timeout = 1;
+
+  // If set, returns a message specifying which part of the speech adaptation
+  // request timed out.
+  string timeout_message = 4;
+}
diff --git a/protos/google/cloud/speech/v1/resource.proto b/protos/google/cloud/speech/v1/resource.proto
@@ -120,19 +120,30 @@ message PhraseSet {
 
 // Speech adaptation configuration.
 message SpeechAdaptation {
+  message ABNFGrammar {
+    // All declarations and rules of an ABNF grammar broken up into multiple
+    // strings that will end up concatenated.
+    repeated string abnf_strings = 1;
+  }
+
   // A collection of phrase sets. To specify the hints inline, leave the
   // phrase set's `name` blank and fill in the rest of its fields. Any
   // phrase set can use any custom class.
   repeated PhraseSet phrase_sets = 1;
 
   // A collection of phrase set resource names to use.
   repeated string phrase_set_references = 2 [(google.api.resource_reference) = {
-                                               type: "speech.googleapis.com/PhraseSet"
-                                             }];
+    type: "speech.googleapis.com/PhraseSet"
+  }];
 
   // A collection of custom classes. To specify the classes inline, leave the
   // class' `name` blank and fill in the rest of its fields, giving it a unique
   // `custom_class_id`. Refer to the inline defined class in phrase hints by its
   // `custom_class_id`.
   repeated CustomClass custom_classes = 3;
+
+  // Augmented Backus-Naur form (ABNF) is a standardized grammar notation
+  // comprised by a set of derivation rules.
+  // See specifications: https://www.w3.org/TR/speech-grammar
+  ABNFGrammar abnf_grammar = 4;
 }
diff --git a/protos/google/cloud/speech/v1p1beta1/cloud_speech.proto b/protos/google/cloud/speech/v1p1beta1/cloud_speech.proto
@@ -266,8 +266,7 @@ message RecognitionConfig {
 
   // The number of channels in the input audio data.
   // ONLY set this for MULTI-CHANNEL recognition.
-  // Valid values for LINEAR16 and FLAC are `1`-`8`.
-  // Valid values for OGG_OPUS are '1'-'254'.
+  // Valid values for LINEAR16, OGG_OPUS and FLAC are `1`-`8`.
   // Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
   // If `0` or omitted, defaults to one channel (mono).
   // Note: We only recognize the first channel by default.
@@ -679,6 +678,13 @@ message RecognizeResponse {
 
   // When available, billed audio seconds for the corresponding request.
   google.protobuf.Duration total_billed_time = 3;
+
+  // Provides information on adaptation behavior in response
+  SpeechAdaptationInfo speech_adaptation_info = 7;
+
+  // The ID associated with the request. This is a unique ID specific only to
+  // the given request.
+  int64 request_id = 8;
 }
 
 // The only message returned to the client by the `LongRunningRecognize` method.
@@ -699,6 +705,13 @@ message LongRunningRecognizeResponse {
 
   // If the transcript output fails this field contains the relevant error.
   google.rpc.Status output_error = 7;
+
+  // Provides information on speech adaptation behavior in response
+  SpeechAdaptationInfo speech_adaptation_info = 8;
+
+  // The ID associated with the request. This is a unique ID specific only to
+  // the given request.
+  int64 request_id = 9;
 }
 
 // Describes the progress of a long-running `LongRunningRecognize` call. It is
@@ -804,6 +817,13 @@ message StreamingRecognizeResponse {
   // When available, billed audio seconds for the stream.
   // Set only if this is the last response in the stream.
   google.protobuf.Duration total_billed_time = 5;
+
+  // Provides information on adaptation behavior in response
+  SpeechAdaptationInfo speech_adaptation_info = 9;
+
+  // The ID associated with the request. This is a unique ID specific only to
+  // the given request.
+  int64 request_id = 10;
 }
 
 // A streaming speech recognition result corresponding to a portion of the audio
@@ -927,3 +947,14 @@ message WordInfo {
   // top alternative.
   int32 speaker_tag = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
+
+// Information on speech adaptation use in results
+message SpeechAdaptationInfo {
+  // Whether there was a timeout when applying speech adaptation. If true,
+  // adaptation had no effect in the response transcript.
+  bool adaptation_timeout = 1;
+
+  // If set, returns a message specifying which part of the speech adaptation
+  // request timed out.
+  string timeout_message = 4;
+}
diff --git a/protos/google/cloud/speech/v1p1beta1/resource.proto b/protos/google/cloud/speech/v1p1beta1/resource.proto
@@ -120,21 +120,32 @@ message PhraseSet {
 
 // Speech adaptation configuration.
 message SpeechAdaptation {
+  message ABNFGrammar {
+    // All declarations and rules of an ABNF grammar broken up into multiple
+    // strings that will end up concatenated.
+    repeated string abnf_strings = 1;
+  }
+
   // A collection of phrase sets. To specify the hints inline, leave the
   // phrase set's `name` blank and fill in the rest of its fields. Any
   // phrase set can use any custom class.
   repeated PhraseSet phrase_sets = 1;
 
   // A collection of phrase set resource names to use.
   repeated string phrase_set_references = 2 [(google.api.resource_reference) = {
-                                               type: "speech.googleapis.com/PhraseSet"
-                                             }];
+    type: "speech.googleapis.com/PhraseSet"
+  }];
 
   // A collection of custom classes. To specify the classes inline, leave the
   // class' `name` blank and fill in the rest of its fields, giving it a unique
   // `custom_class_id`. Refer to the inline defined class in phrase hints by its
   // `custom_class_id`.
   repeated CustomClass custom_classes = 3;
+
+  // Augmented Backus-Naur form (ABNF) is a standardized grammar notation
+  // comprised by a set of derivation rules.
+  // See specifications: https://www.w3.org/TR/speech-grammar
+  ABNFGrammar abnf_grammar = 4;
 }
 
 // Transcription normalization configuration. Use transcription normalization