Update app.py

app.py

@@ -38,6 +38,8 @@ def synthesise(text):
     with torch.no_grad():
         outputs = model_mms(input_ids)
     print("mms model", outputs)
+    print(outputs.audio[0])
+    return outputs.audio[0].cpu()
     inputs = processor(text=text, return_tensors="pt")
     speech = model.generate_speech(inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder)
     print("speecht5 model", speech)