Update app.py

app.py

@@ -3,6 +3,11 @@ from transformers import pipeline
 
 pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
 
+from phonemizer.backend import EspeakBackend
+import os
+
+os.environ["PHONEMIZER_BACKEND"] = "espeak"
+
 narrator = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")
 
 def launch(input_image):