Update `sv.py`

sv.py

@@ -92,22 +92,25 @@ event_set = {"🎼", "👏", "😀", "😭", "🤧", "😷"}
 
 
 def format_str_v2(s):
-    sptk_dict = {}
+    sptk_dict = {sptk: s.count(sptk) for sptk in emoji_dict}
+
     for sptk in emoji_dict:
-        sptk_dict[sptk] = s.count(sptk)
         s = s.replace(sptk, "")
+
     emo = "<|NEUTRAL|>"
     for e in emo_dict:
-        if sptk_dict[e] > sptk_dict[emo]:
+        if sptk_dict.get(e, 0) > sptk_dict.get(emo, 0):
             emo = e
-    for e in event_dict:
-        if sptk_dict[e] > 0:
-            s = event_dict[e] + s
-    s = s + emo_dict[emo]
+
+    s = (
+        "".join(event_dict[e] for e in event_dict if sptk_dict.get(e, 0) > 0)
+        + s
+        + emo_dict[emo]
+    )
 
     for emoji in emo_set.union(event_set):
-        s = s.replace(" " + emoji, emoji)
-        s = s.replace(emoji + " ", emoji)
+        s = s.replace(f" {emoji}", emoji).replace(f"{emoji} ", emoji)
+
     return s.strip()
 
 
@@ -302,6 +305,10 @@ def process_audio(audio_path, language="yue", fs=16000):
                 merge_vad=True,
             )
             text = text[0]["text"]
+
+            # Print the text before format_str_v3
+            print(f"Text before format_str_v3: {text}")
+
             text = format_str_v3(text)
 
             # Handle empty transcriptions