Update app.py

app.py

@@ -31,6 +31,12 @@ def predict(audio_file_pth):
 title = "Music Spectrogram Diffusion: Multi-instrument Music Synthesis with Spectrogram Diffusion"
 
 description = """
+<p>For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
+<br/>
+<a href="https://huggingface.co/spaces/reach-vb/music-spectrogram-diffusion?duplicate=true">
+<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
+</p>
+
 In this work, the authors focus on a middle ground of neural synthesizers that can generate audio from MIDI sequences with arbitrary combinations of instruments in realtime. 
 This enables training on a wide range of transcription datasets with a single model, which in turn offers note-level control of composition and instrumentation across a wide range of instruments.
 
@@ -39,12 +45,6 @@ They use a simple two-stage process: MIDI to spectrograms with an encoder-decode
 
 examples = ["examples/beethoven_mond_2.mid", "examples/beethoven_hammerklavier_2.mid"]
 
-gr.HTML("""
-<p>For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
-<br/>
-<a href="https://huggingface.co/spaces/reach-vb/music-spectrogram-diffusion?duplicate=true">
-<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
-</p>""")
 
 article = """
 <div style='margin:20px auto;'>