Update main.py

main.py

@@ -83,7 +83,7 @@ async def inference(request: InferenceRequest):
 
     output_tokens = results[0].hypotheses[0]
     output_text = inferenceTokenizer.decode(
-        inferenceTokenizer.convert_tokens_to_ids(output_tokens))
+        inferenceTokenizer.convert_tokens_to_ids(output_tokens), skip_special_tokens=True)
 
     # create response
     return {