Update app.py

app.py

@@ -61,11 +61,12 @@ def inference(audio, state=""):
     
     # length penalty for gpt2.generate??? 
     #Prompt
-    generated_outputs = gpt2.generate(input_ids, do_sample=True, num_return_sequences=3, output_scores=True, max_length=4)[:-4]
+    generated_outputs = gpt2.generate(input_ids, do_sample=True, num_return_sequences=3, output_scores=True, max_length=4)
+    outputs = [generated_output[-4:] for generated_output in generated_outputs.tolist()]
     # print("outputs generated ", generated_outputs[0])
     # only use id's that were generated
     # gen_sequences has shape [3, 15]
-    gen_sequences = generated_outputs.sequences[:, input_ids.shape[-1]:]
+    gen_sequences = outputs.sequences[:, input_ids.shape[-1]:]
     print("gen sequences: ", gen_sequences)
     
     # let's stack the logits generated at each step to a tensor and transform