Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline | |
| from gtts import gTTS | |
| import io | |
| from PIL import Image | |
| # Install PyTorch | |
| try: | |
| import torch | |
| except ImportError: | |
| st.warning("PyTorch is not installed. Installing PyTorch...") | |
| import subprocess | |
| subprocess.run(["pip", "install", "torch"]) | |
| st.success("PyTorch has been successfully installed!") | |
| import torch | |
| # Load the image captioning model | |
| caption_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base") | |
| # Load the DeepSeek model for story generation | |
| story_generator = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1", trust_remote_code=True) | |
| def generate_caption(image): | |
| # Generate the caption for the uploaded image | |
| caption = caption_model(image)[0]["generated_text"] | |
| return caption | |
| def generate_story(caption): | |
| # Generate the story based on the caption using the DeepSeek model | |
| prompt = f"Imagine you are a storyteller for young children. Based on the image described as '{caption}', create a short and interesting story for children aged 3-10. Keep it positive and happy in tone." | |
| messages = [{"role": "user", "content": prompt}] | |
| story = story_generator(messages)[0]["generated_text"] | |
| return story | |
| def convert_to_audio(story): | |
| # Convert the story to audio using gTTS | |
| tts = gTTS(text=story, lang="en") | |
| audio_bytes = io.BytesIO() | |
| tts.write_to_fp(audio_bytes) | |
| audio_bytes.seek(0) | |
| return audio_bytes | |
| def main(): | |
| st.title("Storytelling Application") | |
| # File uploader for the image (restricted to JPG) | |
| uploaded_image = st.file_uploader("Upload an image", type=["jpg"]) | |
| if uploaded_image is not None: | |
| # Convert the uploaded image to PIL image | |
| image = Image.open(uploaded_image) | |
| # Display the uploaded image | |
| st.image(image, caption="Uploaded Image", use_container_width=True) | |
| # Generate the caption for the image | |
| caption = generate_caption(image) | |
| st.subheader("Generated Caption:") | |
| st.write(caption) | |
| # Generate the story based on the caption using the DeepSeek model | |
| story = generate_story(caption) | |
| st.subheader("Generated Story:") | |
| st.write(story) | |
| # Convert the story to audio | |
| audio_bytes = convert_to_audio(story) | |
| # Display the audio player | |
| st.audio(audio_bytes, format="audio/mp3") | |
| if __name__ == "__main__": | |
| main() |