Update app.py

app.py

@@ -7,6 +7,7 @@ from transformers import pipeline
 import torch
 from transformers import AutoModelForCausalLM
 from transformers import AutoTokenizer
+import streaming.py
 # from next_word_prediction import GPT2
 
 
@@ -77,7 +78,7 @@ def inference(audio):
     ### end code
     # print audio data as text
     # print(result.text)
-    getText = generator(result.text, max_length=3, num_return_sequences=5)
+    getText = generator(result.text, max_new_tokens=10, num_return_sequences=5)
     pprint(getText)
     return getText, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)