Update app.py

app.py

@@ -27,11 +27,6 @@ For example, you may want to process text and store the entities in different co
 [Want to train a sparse model on your data? Checkout the documentation on sparse transfer learning](https://docs.neuralmagic.com/use-cases/natural-language-processing/question-answering)
 '''
 task = "ner"
-dense_qa_pipeline = Pipeline.create(
-        task=task,
-        model_path="zoo:nlp/token_classification/bert-base/pytorch/huggingface/conll2003/base-none",
-    )
-
 sparse_qa_pipeline = Pipeline.create(
         task=task,
         model_path="zoo:nlp/token_classification/bert-base/pytorch/huggingface/conll2003/12layer_pruned80_quant-none-vnni",
@@ -65,28 +60,15 @@ def map_ner(inference):
   return entities
       
 def run_pipeline(text):
-    dense_start = time.perf_counter()
-    
-    dense_output = dense_qa_pipeline(text)
-    dense_entities = map_ner(dense_output)
-        
-    dense_output = {"text": text, "entities": dense_entities}
-        
-    dense_end = time.perf_counter()
-    dense_duration = (dense_end - dense_start) * 1000.0
-
     sparse_start = time.perf_counter()
-    
     sparse_output = sparse_qa_pipeline(text)
     sparse_entities = map_ner(sparse_output)
-
     sparse_output = {"text": text, "entities": sparse_entities}
-        
     sparse_result = dict(sparse_output)
     sparse_end = time.perf_counter()
     sparse_duration = (sparse_end - sparse_start) * 1000.0
     
-    return sparse_output, sparse_duration, dense_output, dense_duration
+    return sparse_output, sparse_duration
 
 
 with gr.Blocks() as demo:       
@@ -113,7 +95,7 @@ with gr.Blocks() as demo:
     btn.click(
         run_pipeline,
         inputs=[text],
-        outputs=[sparse_answers,sparse_duration,dense_answers,dense_duration],
+        outputs=[sparse_answers,sparse_duration],
     )
 
 if __name__ == "__main__":