Update app.py

app.py

@@ -9,18 +9,18 @@ def img2text(url):
 def text2story(text):
     story_generator = pipeline("text-generation", model="pranavpsv/gpt2-genre-story-generator", device_map="auto", return_full_text=False)
     prompt = f"Create a story under 100 words about the scene: {text}."
-    generated = story_generator(prompt, max_new_tokens=140, do_sample=True, temperature=0.7)
+    generated = story_generator(prompt, max_new_tokens=130, do_sample=True, temperature=0.7)
     story_text = generated[0]['generated_text']
     return story_text
 
 def text2audio(story_text):
-    audio_generator = pipeline("text-to-speech", model="facebook/mms-tts-eng")
+    audio_generator = pipeline("text-to-speech", model="hexgrad/Kokoro-82M")
     audio_output = audio_generator(story_text)
     return audio_output
 
-st.set_page_config(page_title="Once Upon A Time - Storytelling Application", page_icon="📖🏰🦄🧙")
-st.header("Create a story of yours with an image!")
-uploaded_file = st.file_uploader("Upload an image of your story!")
+st.set_page_config(page_title="Once Upon A Time - Storytelling Application", page_icon="📖")
+st.header("Create a story of yours with an image!🏰🦄🧙")
+uploaded_file = st.file_uploader("Upload an image for creating your story!")
 
 if uploaded_file is not None:
     print(uploaded_file)
@@ -29,14 +29,13 @@ if uploaded_file is not None:
         file.write(bytes_data)
     st.image(uploaded_file, caption="Uploaded Image", use_container_width=True)
 
-    st.text('Processing img2text...')
+    st.text('Entering the scene...')
     scenario = img2text(uploaded_file.name)
     st.write(scenario)
 
-    st.text('Generating a story...')
+    st.text('Your story is going to begin...')
     story = text2story(scenario)
     st.write(story)
 
-    st.text('Generating audio data...')
     audio_data = text2audio(story)
     st.audio(audio_data['audio'], format="audio/wav", start_time=0, sample_rate = audio_data['sampling_rate'])