Upload 2 files

app.py

@@ -0,0 +1,45 @@
+import streamlit as st
+from transformers import pipeline
+
+def img2text(url):
+    image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    text = image_to_text_model(url)[0]["generated_text"]
+    return text
+
+def text2story(text):
+    story_text = pipeline("text-generation", model="meta-llama/Meta-Llama-3-8B")
+    story_text = pipeline("Create a story of maximum 100 words based upon {text}")
+    return story_text
+
+def text2audio(story_text):
+    audio_data = pipeline("text-to-speech", model="ElvisTsang/facebook-mms-tts-eng")
+    return audio_data
+
+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!")
+
+if uploaded_file is not None:
+    print(uploaded_file)
+    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)
+
+    st.text('Processing img2text...')
+    scenario = img2text(uploaded_file.name)
+    st.write(scenario)
+
+    st.text('Generating a story...')
+    story = text2story(scenario)
+    st.write(story)
+
+    st.text('Generating audio data...')
+    audio_data =text2audio(story)
+
+    if st.button("Story Time!"):
+        st.audio(audio_data['audio'],
+                    format="audio/wav",
+                    start_time=0,
+                    sample_rate = audio_data['sampling_rate'])
+        st.audio(audio_data)

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+transformers
+torch
+torchaudio