feat(proto): add speaker field to TranscriptSegment for diarization

Add speaker field to the gRPC TranscriptSegment message and map it
through the Go schema, enabling backends to return speaker labels.

Signed-off-by: eureka928 <meobius123@gmail.com>

backend/backend.proto

@@ -299,6 +299,7 @@ message TranscriptSegment {
   int64 end = 3;
   string text = 4;
   repeated int32 tokens = 5;
+  string speaker = 6;
 }
 
 message GenerateImageRequest {

core/backend/transcript.go

@@ -49,11 +49,12 @@ func ModelTranscription(audio, language string, translate, diarize bool, prompt
 		}
 		tr.Segments = append(tr.Segments,
 			schema.TranscriptionSegment{
-				Text:   s.Text,
-				Id:     int(s.Id),
-				Start:  time.Duration(s.Start),
-				End:    time.Duration(s.End),
-				Tokens: tks,
+				Text:    s.Text,
+				Id:      int(s.Id),
+				Start:   time.Duration(s.Start),
+				End:     time.Duration(s.End),
+				Tokens:  tks,
+				Speaker: s.Speaker,
 			})
 	}
 	return tr, err

core/schema/transcription.go

@@ -3,11 +3,12 @@ package schema
 import "time"
 
 type TranscriptionSegment struct {
-	Id     int           `json:"id"`
-	Start  time.Duration `json:"start"`
-	End    time.Duration `json:"end"`
-	Text   string        `json:"text"`
-	Tokens []int         `json:"tokens"`
+	Id      int           `json:"id"`
+	Start   time.Duration `json:"start"`
+	End     time.Duration `json:"end"`
+	Text    string        `json:"text"`
+	Tokens  []int         `json:"tokens"`
+	Speaker string        `json:"speaker,omitempty"`
 }
 
 type TranscriptionResult struct {