Update app.py

app.py

@@ -8,6 +8,9 @@ from espnet2.bin.tts_inference import Text2Speech
 from espnet2.utils.types import str_or_none
 import call_labels
 
+# call the labels (data set from: https://www.kaggle.com/itsahmad/indoor-scenes-cvpr-2019)
+labels = call_labels.call_labels()
+
 # define the feature extractor
 ViT_extractor = AutoFeatureExtractor.from_pretrained('vincentclaes/mit-indoor-scenes')