Update app.py

app.py

@@ -13,7 +13,7 @@ import gradio as gr
 def speech_file_to_array_fn(path, sampling_rate):
     speech_array, _sampling_rate = torchaudio.load(path)
     resampler = torchaudio.transforms.Resample(_sampling_rate)
-    speech = resampler(speech_array).squeeze().numpy()
+    speech = resampler(speech_array[1]).squeeze().numpy()
     return speech
 
 def predict(path, sampling_rate, feature_extractor, device, model, config):