chore(hand edits): apply speech to text hand edits

Author: jeff-arn

speech-to-text/src/main/java/com/ibm/watson/speech_to_text/v1/SpeechToText.java

@@ -72,6 +72,7 @@
 import com.ibm.watson.speech_to_text.v1.model.RecognitionJob;
 import com.ibm.watson.speech_to_text.v1.model.RecognitionJobs;
 import com.ibm.watson.speech_to_text.v1.model.RecognizeOptions;
+import com.ibm.watson.speech_to_text.v1.model.RecognizeWithWebsocketsOptions;
 import com.ibm.watson.speech_to_text.v1.model.RegisterCallbackOptions;
 import com.ibm.watson.speech_to_text.v1.model.RegisterStatus;
 import com.ibm.watson.speech_to_text.v1.model.ResetAcousticModelOptions;
@@ -87,10 +88,15 @@
 import com.ibm.watson.speech_to_text.v1.model.UpgradeLanguageModelOptions;
 import com.ibm.watson.speech_to_text.v1.model.Word;
 import com.ibm.watson.speech_to_text.v1.model.Words;
+import com.ibm.watson.speech_to_text.v1.websocket.RecognizeCallback;
+import com.ibm.watson.speech_to_text.v1.websocket.SpeechToTextWebSocketListener;
 import java.util.HashMap;
 import java.util.Map;
 import java.util.Map.Entry;
-import okhttp3.MultipartBody;
+import okhttp3.HttpUrl;
+import okhttp3.OkHttpClient;
+import okhttp3.Request;
+import okhttp3.WebSocket;
 
 /**
  * The IBM Watson™ Speech to Text service provides APIs that use IBM's speech-recognition
@@ -180,6 +186,58 @@ public SpeechToText(String serviceName, Authenticator authenticator) {
     this.configureService(serviceName);
   }
 
+  /**
+   * Sends audio and returns transcription results for recognition requests over a WebSocket
+   * connection. Requests and responses are enabled over a single TCP connection that abstracts much
+   * of the complexity of the request to offer efficient implementation, low latency, high
+   * throughput, and an asynchronous response. By default, only final results are returned for any
+   * request; to enable interim results, set the interimResults parameter to true.
+   *
+   * <p>The service imposes a data size limit of 100 MB per utterance (per recognition request). You
+   * can send multiple utterances over a single WebSocket connection. The service automatically
+   * detects the endianness of the incoming audio and, for audio that includes multiple channels,
+   * downmixes the audio to one-channel mono during transcoding. (For the audio/l16 format, you can
+   * specify the endianness.)
+   *
+   * @param recognizeOptions the recognize options
+   * @param callback the {@link RecognizeCallback} instance where results will be sent
+   * @return the {@link WebSocket}
+   */
+  public WebSocket recognizeUsingWebSocket(
+      RecognizeWithWebsocketsOptions recognizeOptions, RecognizeCallback callback) {
+    com.ibm.cloud.sdk.core.util.Validator.notNull(
+        recognizeOptions, "recognizeOptions cannot be null");
+    com.ibm.cloud.sdk.core.util.Validator.notNull(recognizeOptions.audio(), "audio cannot be null");
+    com.ibm.cloud.sdk.core.util.Validator.notNull(callback, "callback cannot be null");
+
+    HttpUrl.Builder urlBuilder = HttpUrl.parse(getServiceUrl() + "/v1/recognize").newBuilder();
+
+    if (recognizeOptions.model() != null) {
+      urlBuilder.addQueryParameter("model", recognizeOptions.model());
+    }
+    if (recognizeOptions.languageCustomizationId() != null) {
+      urlBuilder.addQueryParameter(
+          "language_customization_id", recognizeOptions.languageCustomizationId());
+    }
+    if (recognizeOptions.acousticCustomizationId() != null) {
+      urlBuilder.addQueryParameter(
+          "acoustic_customization_id", recognizeOptions.acousticCustomizationId());
+    }
+    if (recognizeOptions.baseModelVersion() != null) {
+      urlBuilder.addQueryParameter("base_model_version", recognizeOptions.baseModelVersion());
+    }
+
+    String url = urlBuilder.toString().replace("https://", "wss://");
+    Request.Builder builder = new Request.Builder().url(url);
+
+    setAuthentication(builder);
+    setDefaultHeaders(builder);
+
+    OkHttpClient client = configureHttpClient();
+    return client.newWebSocket(
+        builder.build(), new SpeechToTextWebSocketListener(recognizeOptions, callback));
+  }
+
   /**
    * List models.
    *
@@ -1378,12 +1436,10 @@ public ServiceCall<Void> addCorpus(AddCorpusOptions addCorpusOptions) {
     if (addCorpusOptions.allowOverwrite() != null) {
       builder.query("allow_overwrite", String.valueOf(addCorpusOptions.allowOverwrite()));
     }
-    MultipartBody.Builder multipartBuilder = new MultipartBody.Builder();
-    multipartBuilder.setType(MultipartBody.FORM);
-    okhttp3.RequestBody corpusFileBody =
-        RequestUtils.inputStreamBody(addCorpusOptions.corpusFile(), "text/plain");
-    multipartBuilder.addFormDataPart("corpus_file", "filename", corpusFileBody);
-    builder.body(multipartBuilder.build());
+
+    // hand edit replacement for corpus file serialization
+    builder.body(RequestUtils.inputStreamBody(addCorpusOptions.corpusFile(), "text/plain"));
+
     ResponseConverter<Void> responseConverter = ResponseConverterUtils.getVoid();
     return createServiceCall(builder.build(), responseConverter);
   }

speech-to-text/src/main/java/com/ibm/watson/speech_to_text/v1/model/SpeechRecognitionAlternative.java

@@ -21,10 +21,10 @@ public class SpeechRecognitionAlternative extends GenericModel {
 
   protected String transcript;
   protected Double confidence;
-  protected List<String> timestamps;
+  protected List<SpeechTimestamp> timestamps;
 
   @SerializedName("word_confidence")
-  protected List<String> wordConfidence;
+  protected List<SpeechWordConfidence> wordConfidence;
 
   protected SpeechRecognitionAlternative() {}
 
@@ -62,7 +62,7 @@ public Double getConfidence() {
    *
    * @return the timestamps
    */
-  public List<String> getTimestamps() {
+  public List<SpeechTimestamp> getTimestamps() {
     return timestamps;
   }
 
@@ -76,7 +76,7 @@ public List<String> getTimestamps() {
    *
    * @return the wordConfidence
    */
-  public List<String> getWordConfidence() {
+  public List<SpeechWordConfidence> getWordConfidence() {
     return wordConfidence;
   }
 }

speech-to-text/src/test/java/com/ibm/watson/speech_to_text/v1/SpeechToTextTest.java

@@ -212,7 +212,7 @@ public void testGetModelNoOptions() throws Throwable {
   public void testRecognizeWOptions() throws Throwable {
     // Register a mock response
     String mockResponseBody =
-        "{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [\"timestamps\"], \"word_confidence\": [\"wordConfidence\"]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}";
+        "{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [[\"timestamps\"]], \"word_confidence\": [[\"wordConfidence\"]]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}";
     String recognizePath = "/v1/recognize";
     server.enqueue(
         new MockResponse()
@@ -424,7 +424,7 @@ public void testUnregisterCallbackNoOptions() throws Throwable {
   public void testCreateJobWOptions() throws Throwable {
     // Register a mock response
     String mockResponseBody =
-        "{\"id\": \"id\", \"status\": \"waiting\", \"created\": \"created\", \"updated\": \"updated\", \"url\": \"url\", \"user_token\": \"userToken\", \"results\": [{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [\"timestamps\"], \"word_confidence\": [\"wordConfidence\"]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}], \"warnings\": [\"warnings\"]}";
+        "{\"id\": \"id\", \"status\": \"waiting\", \"created\": \"created\", \"updated\": \"updated\", \"url\": \"url\", \"user_token\": \"userToken\", \"results\": [{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [[\"timestamps\"]], \"word_confidence\": [[\"wordConfidence\"]]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}], \"warnings\": [\"warnings\"]}";
     String createJobPath = "/v1/recognitions";
     server.enqueue(
         new MockResponse()
@@ -542,7 +542,7 @@ public void testCreateJobNoOptions() throws Throwable {
   public void testCheckJobsWOptions() throws Throwable {
     // Register a mock response
     String mockResponseBody =
-        "{\"recognitions\": [{\"id\": \"id\", \"status\": \"waiting\", \"created\": \"created\", \"updated\": \"updated\", \"url\": \"url\", \"user_token\": \"userToken\", \"results\": [{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [\"timestamps\"], \"word_confidence\": [\"wordConfidence\"]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}], \"warnings\": [\"warnings\"]}]}";
+        "{\"recognitions\": [{\"id\": \"id\", \"status\": \"waiting\", \"created\": \"created\", \"updated\": \"updated\", \"url\": \"url\", \"user_token\": \"userToken\", \"results\": [{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [[\"timestamps\"]], \"word_confidence\": [[\"wordConfidence\"]]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}], \"warnings\": [\"warnings\"]}]}";
     String checkJobsPath = "/v1/recognitions";
     server.enqueue(
         new MockResponse()
@@ -587,7 +587,7 @@ public void testCheckJobsWRetries() throws Throwable {
   public void testCheckJobWOptions() throws Throwable {
     // Register a mock response
     String mockResponseBody =
-        "{\"id\": \"id\", \"status\": \"waiting\", \"created\": \"created\", \"updated\": \"updated\", \"url\": \"url\", \"user_token\": \"userToken\", \"results\": [{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [\"timestamps\"], \"word_confidence\": [\"wordConfidence\"]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}], \"warnings\": [\"warnings\"]}";
+        "{\"id\": \"id\", \"status\": \"waiting\", \"created\": \"created\", \"updated\": \"updated\", \"url\": \"url\", \"user_token\": \"userToken\", \"results\": [{\"results\": [{\"final\": true, \"alternatives\": [{\"transcript\": \"transcript\", \"confidence\": 0, \"timestamps\": [[\"timestamps\"]], \"word_confidence\": [[\"wordConfidence\"]]}], \"keywords_result\": {\"mapKey\": [{\"normalized_text\": \"normalizedText\", \"start_time\": 9, \"end_time\": 7, \"confidence\": 0}]}, \"word_alternatives\": [{\"start_time\": 9, \"end_time\": 7, \"alternatives\": [{\"confidence\": 0, \"word\": \"word\"}]}], \"end_of_utterance\": \"end_of_data\"}], \"result_index\": 11, \"speaker_labels\": [{\"from\": 4, \"to\": 2, \"speaker\": 7, \"confidence\": 10, \"final\": true}], \"processing_metrics\": {\"processed_audio\": {\"received\": 8, \"seen_by_engine\": 12, \"transcription\": 13, \"speaker_labels\": 13}, \"wall_clock_since_first_byte_received\": 31, \"periodic\": true}, \"audio_metrics\": {\"sampling_interval\": 16, \"accumulated\": {\"final\": true, \"end_time\": 7, \"signal_to_noise_ratio\": 18, \"speech_ratio\": 11, \"high_frequency_loss\": 17, \"direct_current_offset\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"clipping_rate\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}], \"non_speech_level\": [{\"begin\": 5, \"end\": 3, \"count\": 5}]}}, \"warnings\": [\"warnings\"]}], \"warnings\": [\"warnings\"]}";
     String checkJobPath = "/v1/recognitions/testString";
     server.enqueue(
         new MockResponse()