Update app.py

app.py

@@ -29,7 +29,7 @@ def synthesise(text):
     inputs = processor(text=text, return_tensors="pt")
     outputs = model(input_ids=inputs["input_ids"].to(device), speaker_id=speaker_embeddings.to(device))
     speech = outputs["waveform"]
-    return speech.detach().cpu()
+    return speech.squeeze(0).detach().cpu()
 
 
 target_dtype = np.int16