Update app.py

app.py

@@ -31,7 +31,7 @@ def synthesise(text):
 
     with torch.no_grad():
         output = model(**inputs)
-        output = output.waveform
+        output = output.waveform[0]
     # inputs = processor(text=text, return_tensors="pt")
     # speech = model.generate_speech(inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder)
     return output.cpu()
@@ -65,7 +65,7 @@ file_translate = gr.Interface(
     fn=speech_to_speech_translation,
     inputs=gr.Audio(source="upload", type="filepath"),
     outputs=gr.Audio(label="Generated Speech", type="numpy"),
-    # examples=[["./example.wav"]],
+    examples=[["./example.wav"]],
     title=title,
     description=description,
 )