Update app.py

app.py

@@ -11,6 +11,7 @@ import warnings
 warnings.filterwarnings("ignore")
 
 # Image-to-text
+@spaces.GPU
 def img2txt(url):
     print("Initializing captioning model...")
     captioning_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
@@ -22,6 +23,7 @@ def img2txt(url):
     return text
 
 # Text-to-story
+@spaces.GPU
 def txt2story(img_text, top_k, top_p, temperature):
 
     headers = {"Authorization": f"Bearer {os.environ['TOGETHER_API_KEY']}"}
@@ -45,6 +47,7 @@ def txt2story(img_text, top_k, top_p, temperature):
 
 
 # Text-to-speech
+@spaces.GPU
 def txt2speech(text):
     print("Initializing text-to-speech conversion...")
     API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
@@ -80,7 +83,6 @@ def main():
         st.image(uploaded_file, caption='🖼️ Uploaded Image', use_column_width=True)
 
         # Initiates AI processing and story generation
-        @spaces.GPU
         with st.spinner("## 🤖 AI is at Work! "):
             scenario = img2txt("uploaded_image.jpg")  # Extracts text from the image
             story = txt2story(scenario, top_k, top_p, temperature)  # Generates a story based on the image text, LLM params