feat: update emotion handling in audiobook segments and UI for multi-emotion selection

qwen3-tts-backend/core/tts_service.py

@@ -445,19 +445,35 @@ class IndexTTS2Backend:
 
     @staticmethod
     def _emo_text_to_vector(emo_text: str) -> Optional[list]:
-        text = emo_text.lower()
+        tokens = [t.strip() for t in emo_text.split('+') if t.strip()]
         matched = []
-        for idx, words in enumerate(IndexTTS2Backend._EMO_KEYWORDS):
-            for word in words:
-                if word in text:
-                    matched.append(idx)
-                    break
+        for tok in tokens:
+            if ':' in tok:
+                name_part, w_str = tok.rsplit(':', 1)
+                try:
+                    weight: Optional[float] = float(w_str)
+                except ValueError:
+                    weight = None
+            else:
+                name_part = tok
+                weight = None
+            name_lower = name_part.lower().strip()
+            for idx, words in enumerate(IndexTTS2Backend._EMO_KEYWORDS):
+                for word in words:
+                    if word in name_lower:
+                        matched.append((idx, weight))
+                        break
         if not matched:
             return None
         vec = [0.0] * 8
-        score = 0.8 if len(matched) == 1 else 0.5
-        for idx in matched:
-            vec[idx] = 0.2 if idx == 1 else score
+        has_explicit = any(w is not None for _, w in matched)
+        if has_explicit:
+            for idx, w in matched:
+                vec[idx] = w if w is not None else 0.5
+        else:
+            score = 0.8 if len(matched) == 1 else 0.5
+            for idx, _ in matched:
+                vec[idx] = 0.2 if idx == 1 else score
         return vec
 
     async def generate(