fix README.md: using with stable-audio-3 code block style

README.md

@@ -34,6 +34,7 @@ This model can be used with:
 
 
 ### Using with `stable-audio-3`
+```python
 import torchaudio
 from stable_audio_3 import AutoencoderModel
 
@@ -41,7 +42,7 @@ ae = AutoencoderModel.from_pretrained("same-l")
 waveform, sr = torchaudio.load("audio.wav")
 latents = ae.encode(waveform, sr)
 audio_out = ae.decode(latents)
-
+```
 
 ### Using with `stable-audio-tools`