feat: add model and language_codes fields in RecognitionConfig message + enable default _ recognizer

Google APIs · copybara-github · commit e73fc8ff3b5c · 2023-07-05T09:29:15.000-07:00
Enables specifying `model` and `language_codes` in requests without having to specify them in the Recognizer (they can still be specified in the Recognizer in the `default_recognition_config` field).

Also enables using the recognizer ID `_` to perform recognition without explicitly creating a Recognizer resource.

The top-level `model` and `language_codes` fields are deprecated in favor of the new fields added in the `RecognitionConfig` message. The old fields continue to work.

PiperOrigin-RevId: 545698919
diff --git a/google/cloud/speech/v2/BUILD.bazel b/google/cloud/speech/v2/BUILD.bazel
@@ -225,7 +225,9 @@ php_gapic_library(
     rest_numeric_enums = True,
     service_yaml = "speech_v2.yaml",
     transport = "grpc+rest",
-    deps = [":speech_php_proto"],
+    deps = [
+        ":speech_php_proto",
+    ],
 )
 
 # Open Source Packages
@@ -334,6 +336,7 @@ load(
 
 csharp_proto_library(
     name = "speech_csharp_proto",
+    extra_opts = [],
     deps = [":speech_proto"],
 )
 
diff --git a/google/cloud/speech/v2/cloud_speech.proto b/google/cloud/speech/v2/cloud_speech.proto
@@ -585,7 +585,7 @@ message Recognizer {
   // characters or less.
   string display_name = 3;
 
-  // Required. Which model to use for recognition requests. Select the model
+  // Optional. Which model to use for recognition requests. Select the model
   // best suited to your domain to get best results.
   //
   // Guidance for choosing which model to use can be found in the [Transcription
@@ -594,9 +594,9 @@ message Recognizer {
   // and the models supported in each region can be found in the [Table Of
   // Supported
   // Models](https://cloud.google.com/speech-to-text/v2/docs/speech-to-text-supported-languages).
-  string model = 4 [(google.api.field_behavior) = REQUIRED];
+  string model = 4 [deprecated = true, (google.api.field_behavior) = OPTIONAL];
 
-  // Required. The language of the supplied audio as a
+  // Optional. The language of the supplied audio as a
   // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
   //
   // Supported languages for each model are listed in the [Table of Supported
@@ -608,7 +608,8 @@ message Recognizer {
   // When you create or update a Recognizer, these values are
   // stored in normalized BCP-47 form. For example, "en-us" is stored as
   // "en-US".
-  repeated string language_codes = 17 [(google.api.field_behavior) = REQUIRED];
+  repeated string language_codes = 17
+      [deprecated = true, (google.api.field_behavior) = OPTIONAL];
 
   // Default configuration to use for requests with this Recognizer.
   // This can be overwritten by inline configuration in the
@@ -867,6 +868,30 @@ message RecognitionConfig {
     ExplicitDecodingConfig explicit_decoding_config = 8;
   }
 
+  // Optional. Which model to use for recognition requests. Select the model
+  // best suited to your domain to get best results.
+  //
+  // Guidance for choosing which model to use can be found in the [Transcription
+  // Models
+  // Documentation](https://cloud.google.com/speech-to-text/v2/docs/transcription-model)
+  // and the models supported in each region can be found in the [Table Of
+  // Supported
+  // Models](https://cloud.google.com/speech-to-text/v2/docs/speech-to-text-supported-languages).
+  string model = 9 [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. The language of the supplied audio as a
+  // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
+  // Language tags are normalized to BCP-47 before they are used eg "en-us"
+  // becomes "en-US".
+  //
+  // Supported languages for each model are listed in the [Table of Supported
+  // Models](https://cloud.google.com/speech-to-text/v2/docs/speech-to-text-supported-languages).
+  //
+  // If additional languages are provided, recognition result will contain
+  // recognition in the most likely language detected. The recognition result
+  // will include the language tag of the language detected in the audio.
+  repeated string language_codes = 10 [(google.api.field_behavior) = OPTIONAL];
+
   // Speech recognition features to enable.
   RecognitionFeatures features = 2;
 
@@ -883,7 +908,8 @@ message RecognitionConfig {
 message RecognizeRequest {
   // Required. The name of the Recognizer to use during recognition. The
   // expected format is
-  // `projects/{project}/locations/{location}/recognizers/{recognizer}`.
+  // `projects/{project}/locations/{location}/recognizers/{recognizer}`. The
+  // {recognizer} segment may be set to `_` to use an empty implicit Recognizer.
   string recognizer = 3 [
     (google.api.field_behavior) = REQUIRED,
     (google.api.resource_reference) = {
@@ -1100,24 +1126,27 @@ message StreamingRecognitionConfig {
 // [StreamingRecognize][google.cloud.speech.v2.Speech.StreamingRecognize]
 // method. Multiple
 // [StreamingRecognizeRequest][google.cloud.speech.v2.StreamingRecognizeRequest]
-// messages are sent. The first message must contain a
+// messages are sent in one call.
+//
+// If the [Recognizer][google.cloud.speech.v2.Recognizer] referenced by
+// [recognizer][google.cloud.speech.v2.StreamingRecognizeRequest.recognizer]
+// contains a fully specified request configuration then the stream may only
+// contain messages with only
+// [audio][google.cloud.speech.v2.StreamingRecognizeRequest.audio] set.
+//
+// Otherwise the first message must contain a
 // [recognizer][google.cloud.speech.v2.StreamingRecognizeRequest.recognizer] and
-// optionally a
+// a
 // [streaming_config][google.cloud.speech.v2.StreamingRecognizeRequest.streaming_config]
-// message and must not contain
-// [audio][google.cloud.speech.v2.StreamingRecognizeRequest.audio]. All
-// subsequent messages must contain
-// [audio][google.cloud.speech.v2.StreamingRecognizeRequest.audio] and must not
-// contain a
-// [streaming_config][google.cloud.speech.v2.StreamingRecognizeRequest.streaming_config]
-// message.
+// message that together fully specify the request configuration and must not
+// contain [audio][google.cloud.speech.v2.StreamingRecognizeRequest.audio]. All
+// subsequent messages must only have
+// [audio][google.cloud.speech.v2.StreamingRecognizeRequest.audio] set.
 message StreamingRecognizeRequest {
-  // Required. Streaming recognition should start with an initial request having
-  // a `recognizer`. Subsequent requests carry the audio data to be recognized.
-  //
-  // The initial request with configuration can be omitted if the Recognizer
-  // being used has a
-  // [default_recognition_config][google.cloud.speech.v2.Recognizer.default_recognition_config].
+  // Required. The name of the Recognizer to use during recognition. The
+  // expected format is
+  // `projects/{project}/locations/{location}/recognizers/{recognizer}`. The
+  // {recognizer} segment may be set to `_` to use an empty implicit Recognizer.
   string recognizer = 3 [
     (google.api.field_behavior) = REQUIRED,
     (google.api.resource_reference) = {
@@ -1152,7 +1181,10 @@ message BatchRecognizeRequest {
     DYNAMIC_BATCHING = 1;
   }
 
-  // Required. Resource name of the recognizer to be used for ASR.
+  // Required. The name of the Recognizer to use during recognition. The
+  // expected format is
+  // `projects/{project}/locations/{location}/recognizers/{recognizer}`. The
+  // {recognizer} segment may be set to `_` to use an empty implicit Recognizer.
   string recognizer = 1 [
     (google.api.field_behavior) = REQUIRED,
     (google.api.resource_reference) = {
diff --git a/google/cloud/speech/v2/speech_v2.yaml b/google/cloud/speech/v2/speech_v2.yaml
@@ -39,6 +39,10 @@ backend:
   - selector: google.cloud.location.Locations.ListLocations
     deadline: 355.0
   - selector: 'google.cloud.speech.v2.Speech.*'
+    deadline: 10.0
+  - selector: google.cloud.speech.v2.Speech.Recognize
+    deadline: 185.0
+  - selector: google.cloud.speech.v2.Speech.StreamingRecognize
     deadline: 355.0
   - selector: 'google.longrunning.Operations.*'
     deadline: 355.0
