Update app.py

app.py

@@ -49,8 +49,13 @@ def inference(audio):
     ### code 
     input_ids = tokenizer(prompt, result.text, return_tensors="pt").input_ids
     print("inputs ", input_ids)
+
+    # prompt length
+    prompt_length = len(tokenizer.decode(inputs_ids[0]))
+    
     # length penalty for gpt2.generate??? 
-    generated_outputs = gpt2.generate(input_ids, do_sample=True, num_return_sequences=3, output_scores=True)
+    #Prompt
+    generated_outputs = prompt + gpt2.generate(input_ids, do_sample=True, num_return_sequences=3, output_scores=True)
     print("outputs generated ", generated_outputs[0])
     # only use id's that were generated
     # gen_sequences has shape [3, 15]