Upload 2 files

app.py

@@ -0,0 +1,72 @@
+from dotenv import find_dotenv, load_dotenv
+from transformers import pipeline
+from langchain import PromptTemplate, LLMChain, OpenAI
+import requests
+import os
+import streamlit as st
+
+load_dotenv(find_dotenv())
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+#module1: image to text
+def imgtotxt(url):
+    img_to_txt = pipeline("image-to-text",model="Salesforce/blip-image-captioning-base")
+    text = img_to_txt(url)[0]["generated_text"]
+    print(text)
+    return text
+
+
+#module2: llm
+def generate_story(scenario):
+    template = """
+    You are a story teller;
+    You can generate a short story based on a simple narrative, the story should be no more than 50 words;
+
+    CONTEXT: {scenario}
+    STORY:
+    """
+
+    prompt = PromptTemplate(template=template, input_variables=["scenario"])
+
+    story_llm = LLMChain(llm=OpenAI(model_name="gpt-3.5-turbo", temperature=1), prompt=prompt, verbose=True)
+    story = story_llm.predict(scenario=scenario)
+
+    print(story)
+    return story
+
+
+#module3: text to speech
+def texttospeech(message):
+    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
+    headers = {"Authorization": f"Bearer {HUGGINGFACEHUB_API_TOKEN}"}
+    payloads = {
+        "inputs": message
+    }
+
+    response = requests.post(API_URL, headers=headers, json=payloads)
+    with open('audio.flac', 'wb') as file:
+        file.write(response.content)
+
+def main():
+    st.set_page_config(page_title="Image to Audio Story", page_icon="🗣️")
+    st.header("Turn Image into Audio Story")
+    uploaded_file = st.file_uploader("Choose an Image...", type="jpg")
+
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        with open(uploaded_file.name, "wb") as file:
+            file.write(bytes_data)
+        st.image(uploaded_file, caption="Uploaded Image.", use_column_width=True)
+        scenario = imgtotxt(uploaded_file.name)
+        story= generate_story(scenario)
+        texttospeech(story)
+
+        with st.expander("Scenario"):
+            st.write(scenario)
+        with st.expander("Story"):
+            st.write(story)
+
+        st.audio("audio.flac")
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,7 @@
+python-dotenv 
+transformers 
+langchain 
+requests 
+streamlit
+torch
+openai