Update app.py

app.py

@@ -208,7 +208,7 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, exp_name, remove_silence,
             # Calculate duration
             ref_text_len = len(ref_text.encode("utf-8"))
             gen_text_len = len(gen_text.encode("utf-8"))
-            duration = ref_audio_len + int(ref_audio_len / ref_text_len * gen_text_len / speed)
+            duration = ref_audio_len + int(ref_audio_len / ref_text_len * gen_text_len / speed * 0.8)
     # Print the calculated duration
         print(f"Duration: {duration} seconds")
         # inference
@@ -361,7 +361,7 @@ def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence, cross_fa
     audio, sr = torchaudio.load(ref_audio)
 
     # Use the new chunk_text function to split gen_text
-    max_chars = int(0.8(len(ref_text.encode('utf-8')) / (audio.shape[-1] / sr) * (25 - audio.shape[-1] / sr)))
+    max_chars = int(0.8 * (len(ref_text.encode('utf-8')) / (audio.shape[-1] / sr) * (25 - audio.shape[-1] / sr)))
     gen_text_batches = chunk_text(gen_text, max_chars=max_chars)
     print('ref_text', ref_text)
     for i, batch_text in enumerate(gen_text_batches):