fix(speech): move 'speaker_tag' field from 'SpeakerDiarizationConfig' to 'WordInfo' (via synth) (#9576)

Author: yoshi-automation

speech/google/cloud/speech_v1/proto/cloud_speech.proto

@@ -366,14 +366,6 @@ message SpeakerDiarizationConfig {
   // flexibility by allowing the system to automatically determine the correct
   // number of speakers. If not set, the default value is 6.
   int32 max_speaker_count = 3;
-
-  // A distinct integer value is assigned for every speaker within
-  // the audio. This field specifies which one of those speakers was detected to
-  // have spoken this word. Value ranges from '1' to diarization_speaker_count.
-  // speaker_tag is set if enable_speaker_diarization = 'true' and only in the
-  // top alternative.
-  int32 speaker_tag = 5
-    [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // Description of audio data to be recognized.
@@ -752,4 +744,12 @@ message WordInfo {
 
   // The word corresponding to this set of information.
   string word = 3;
+
+  // A distinct integer value is assigned for every speaker within
+  // the audio. This field specifies which one of those speakers was detected to
+  // have spoken this word. Value ranges from '1' to diarization_speaker_count.
+  // speaker_tag is set if enable_speaker_diarization = 'true' and only in the
+  // top alternative.
+  int32 speaker_tag = 5
+    [(google.api.field_behavior) = OUTPUT_ONLY];
 }