Add code

app.py

@@ -213,18 +213,14 @@ def generate_base(subject, setting):
 
     model_input = story.replace("\n", " ").strip()
     model_input_tokens = nltk.sent_tokenize(model_input)
-    model_input_token_pairs = []
-    for i in range(0, len(model_input_tokens), 2):
-        model_input_token_pairs.append(" ".join(model_input_tokens[i:(i + 2)]))
 
-
-    play_steps_in_s = 5.0
+    play_steps_in_s = 3.0
     play_steps = int(frame_rate * play_steps_in_s)
 
     description = "Jenny speaks at an average pace with a calm delivery in a very confined sounding environment with clear audio quality."
     description_tokens = tokenizer(description, return_tensors="pt").to(device)
 
-    for i, sentence in enumerate(model_input_token_pairs):
+    for i, sentence in enumerate(model_input_tokens):
         streamer = ParlerTTSStreamer(model, device=device, play_steps=play_steps)
         print("SENTENCE", sentence)
         prompt = tokenizer(sentence, return_tensors="pt").to(device)