modify markdown

app.py

@@ -158,13 +158,10 @@ with demo:
                 <h2>Overview</h2>
                 
                 BigDL-Nano is a library in [BigDL 2.0](https://github.com/intel-analytics/BigDL) that allows the users to transparently accelerate their deep learning pipelines (including data processing, training and inference) by automatically integrating optimized libraries, best-known configurations, and software optimizations. </p>
-                The animation on the right shows how the user can easily enable training using BigDL-Nano with just one line of change.
+                The video on the right shows how the user can easily accelerate their training and inference (including tracing and quantization) pipelines using BigDL-Nano with just a couple of lines of code; you may refer to our [CVPR 2022 demo paper](https://arxiv.org/abs/2204.01715) for more details.
                 ''')
         with gr.Column():
             gr.Video(value="data/training_api.mp4")
-    gr.Markdown('''
-            The below animation shows how the user can easily enable acceleration and quantization using BigDL-Nano with just a couple of lines of code; you may refer to our [CVPR 2022 demo paper](https://arxiv.org/abs/2204.01715) for more details.
-            ''')
     with gr.Row().style(equal_height=True):
         with gr.Column():
             gr.Video(value="data/openvino_api.mp4")
@@ -173,7 +170,7 @@ with demo:
     gr.Markdown('''
             <h2>Demo</h2>
             
-            This section we show an inference demo by using an image stylization example to demostrate the speedup of the above code when using quantization in BigDL-Nano (about 2~3x inference time speedup). 
+            This section uses an image stylization example to demonstrate the speedup of an inference pipeline using quantization in BigDL-Nano (about 2~3x inference time speedup).
             This inference demo is adapted from the original [FSPBT-Image-Translation code](https://github.com/rnwzd/FSPBT-Image-Translation),
             and the default image is from [the COCO dataset](https://cocodataset.org/#home).
             ''')