feat: add processing strategy to batch recognition requests (#6211)

PiperOrigin-RevId: 530882015 Source-Link: googleapis/googleapis@189bdfa Source-Link: googleapis/googleapis-gen@64c7a84 Copy-Tag: eyJwIjoiU3BlZWNoLy5Pd2xCb3QueWFtbCIsImgiOiI2NGM3YTg0M2FmZGRhOGM2NTFmZmNhNmUxYTM3NGFjNzgwMWQzNzI4In0=
googleapis · May 11, 2023 · 0ef2434 · 0ef2434
1 parent ec90369
commit 0ef2434
Show file tree

Hide file tree

Showing 10 changed files with 176 additions and 238 deletions.
diff --git a/Speech/metadata/V2/CloudSpeech.php b/Speech/metadata/V2/CloudSpeech.php
diff --git a/Speech/samples/V2/SpeechClient/create_recognizer.php b/Speech/samples/V2/SpeechClient/create_recognizer.php
@@ -35,54 +35,17 @@
  * @param string $recognizerModel                Which model to use for recognition requests. Select the model
  *                                               best suited to your domain to get best results.
  *
- *                                               Supported models:
- *
- *                                               - `latest_long`
- *
- *                                               Best for long form content like media or conversation.
- *
- *                                               - `latest_short`
- *
- *                                               Best for short form content like commands or single shot directed speech.
- *                                               When using this model, the service will stop transcribing audio after the
- *                                               first utterance is detected and completed.
- *
- *                                               When using this model,
- *                                               [SEPARATE_RECOGNITION_PER_CHANNEL][google.cloud.speech.v2.RecognitionFeatures.MultiChannelMode.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.
+ *                                               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).
  * @param string $recognizerLanguageCodesElement 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 at:
- *                                               https://cloud.google.com/speech-to-text/docs/languages
+ *                                               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

diff --git a/Speech/samples/V2/SpeechClient/update_recognizer.php b/Speech/samples/V2/SpeechClient/update_recognizer.php
@@ -35,54 +35,17 @@
  * @param string $recognizerModel                Which model to use for recognition requests. Select the model
  *                                               best suited to your domain to get best results.
  *
- *                                               Supported models:
- *
- *                                               - `latest_long`
- *
- *                                               Best for long form content like media or conversation.
- *
- *                                               - `latest_short`
- *
- *                                               Best for short form content like commands or single shot directed speech.
- *                                               When using this model, the service will stop transcribing audio after the
- *                                               first utterance is detected and completed.
- *
- *                                               When using this model,
- *                                               [SEPARATE_RECOGNITION_PER_CHANNEL][google.cloud.speech.v2.RecognitionFeatures.MultiChannelMode.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.
+ *                                               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).
  * @param string $recognizerLanguageCodesElement 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 at:
- *                                               https://cloud.google.com/speech-to-text/docs/languages
+ *                                               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

diff --git a/Speech/src/V2/BatchRecognizeRequest.php b/Speech/src/V2/BatchRecognizeRequest.php
diff --git a/Speech/src/V2/BatchRecognizeRequest/ProcessingStrategy.php b/Speech/src/V2/BatchRecognizeRequest/ProcessingStrategy.php
diff --git a/Speech/src/V2/Gapic/SpeechGapicClient.php b/Speech/src/V2/Gapic/SpeechGapicClient.php
@@ -605,6 +605,9 @@ public function __construct(array $options = [])
      *           The maximum number of files allowed to be specified is 5.
      *     @type RecognitionOutputConfig $recognitionOutputConfig
      *           Configuration options for where to output the transcripts of each file.
+     *     @type int $processingStrategy
+     *           Processing strategy to use for this request.
+     *           For allowed values, use constants defined on {@see \Google\Cloud\Speech\V2\BatchRecognizeRequest\ProcessingStrategy}
      *     @type RetrySettings|array $retrySettings
      *           Retry settings to use for this call. Can be a {@see RetrySettings} object, or an
      *           associative array of retry settings parameters. See the documentation on
@@ -637,6 +640,10 @@ public function batchRecognize($recognizer, array $optionalArgs = [])
             $request->setRecognitionOutputConfig($optionalArgs['recognitionOutputConfig']);
         }
 
+        if (isset($optionalArgs['processingStrategy'])) {
+            $request->setProcessingStrategy($optionalArgs['processingStrategy']);
+        }
+
         $requestParams = new RequestParamsHeaderDescriptor($requestParamHeaders);
         $optionalArgs['headers'] = isset($optionalArgs['headers']) ? array_merge($requestParams->getHeader(), $optionalArgs['headers']) : $requestParams->getHeader();
         return $this->startOperationsCall('BatchRecognize', $optionalArgs, $request, $this->getOperationsClient())->wait();

diff --git a/Speech/src/V2/ListCustomClassesRequest.php b/Speech/src/V2/ListCustomClassesRequest.php