demo

app.py

@@ -21,7 +21,6 @@ speaker_embeddings = {
 def predict(text, speaker):
     if len(text.strip()) == 0:
         return (16000, np.zeros(0).astype(np.int16))
-
     speaker_embedding = np.load(speaker_embeddings[speaker[:3]])
     speaker_embedding = torch.tensor(speaker_embedding).unsqueeze(0)
     inputs = processor(text=text, return_tensors="pt")