Update README.md

README.md

@@ -63,7 +63,7 @@ synthesiser = pipeline("text-to-audio", "facebook/musicgen-large")
 
 music = synthesiser("lo-fi music with a soothing melody", forward_params={"do_sample": True})
 
-scipy.io.wavfile.write("musicgen_out.wav", rate=music["sampling_rate"], music=audio["audio"])
+scipy.io.wavfile.write("musicgen_out.wav", rate=music["sampling_rate"], data=music["audio"])
 ```
 
 3. Run inference via the Transformers modelling code. You can use the processor + generate code to convert text into a mono 32 kHz audio waveform for more fine-grained control.