Update app.py

app.py

@@ -24,11 +24,8 @@ def translate(audio):
     return outputs['text']
     
 def synthesise(text):
-    inputs = tokenizer(text, return_tensors="pt")
-    with torch.no_grad():
-        outputs = model(inputs["input_ids"])
-    speech = outputs.audio[0]
-    
+    inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder)
     return speech.cpu()
 
 def speech_to_speech_translation(audio):