Update src/utils.py

src/utils.py

@@ -52,7 +52,7 @@ def format_timestamp(seconds: float, always_include_hours: bool = False, fractio
 
 
 def write_txt(transcript: Iterator[dict], file: TextIO):
-    converter = opencc.OpenCC('s2twp') #s2twp.json - 簡體到繁體（臺灣正體標準）並轉換爲臺灣常用詞彙
+    converter = opencc.OpenCC('s2tw') #s2tw.json - 簡體到臺灣正體
     for segment in transcript:
         segment_text = converter.convert(segment['text'].strip())
         print(segment_text, file=file, flush=True)
@@ -63,9 +63,11 @@ def write_vtt(transcript: Iterator[dict], file: TextIO,
     iterator  = __subtitle_preprocessor_iterator(transcript, maxLineWidth, highlight_words)
 
     # print("WEBVTT\n", file=file)
+    converter = opencc.OpenCC('s2tw') #s2tw.json - 簡體到臺灣正體
 
     for segment in iterator:
-        text = segment['text'].replace('-->', '->')
+        segment_text = segment['text'].replace('-->', '->')
+        text = converter.convert(segment_text)
 
         print(
             # f"{format_timestamp(segment['start'])} --> {format_timestamp(segment['end'])}\n"
@@ -88,7 +90,7 @@ def write_srt(transcript: Iterator[dict], file: TextIO,
             write_srt(result["segments"], file=srt)
     """
     iterator  = __subtitle_preprocessor_iterator(transcript, maxLineWidth, highlight_words)
-    converter = opencc.OpenCC('s2twp') #s2twp.json - 簡體到繁體（臺灣正體標準）並轉換爲臺灣常用詞彙
+    converter = opencc.OpenCC('s2tw') #s2tw.json - 簡體到臺灣正體
 
     for i, segment in enumerate(iterator, start=1):
         segment_text = segment['text'].replace('-->', '->')