Update app.py

app.py

@@ -159,10 +159,17 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, exp_name, remove_silence,
         final_text_list = convert_char_to_pinyin(text_list)
 
         # Calculate duration
+    #    ref_audio_len = audio.shape[-1] // hop_length
+     #   zh_pause_punc = r"。，、；：？！,"
+      #  gen_text_len = len(gen_text.encode('utf-8')) + 3 * len(re.findall(zh_pause_punc, gen_text))
+      #  duration = min(10, max(1, int(round(gen_text_len / (speed * 10)))))*100
+
+                # Calculate duration
         ref_audio_len = audio.shape[-1] // hop_length
-        zh_pause_punc = r"。，、；：？！,"
+        zh_pause_punc = r"。，、；：？！"
+        ref_text_len = len(ref_text.encode('utf-8')) + 3 * len(re.findall(zh_pause_punc, ref_text))
         gen_text_len = len(gen_text.encode('utf-8')) + 3 * len(re.findall(zh_pause_punc, gen_text))
-        duration = min(10, max(1, int(round(gen_text_len / (speed * 10)))))*100
+        duration = ref_audio_len + int(ref_audio_len / ref_text_len * gen_text_len / speed)
         print(f"Duration: {duration} seconds")
 
         # inference