Update app.py

app.py

@@ -27,7 +27,8 @@ def text2speech(model, text):
         embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
         speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
         output = speechclassifier(text, forward_params={"speaker_embeddings": speaker_embedding})
-        return output["audio"]
+        console.log(output, type(output) )
+        return output
 
 radio1 = gr.Radio(["microsoft/resnet-50", "google/vit-base-patch16-224", "apple/mobilevit-small"], label="Select a Classifier", info="Image Classifier")
 tab1 = gr.Interface(