Upload 2 files

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+from transformers import pipeline
+
+# function part
+# img2text
+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
+
+# text2story
+def text2story(text):
+    text_generation_model = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
+    story_text = text_generation_model(text, min_length=50, max_length=100, do_sample=True, early_stopping=True, top_p=0.4)[0]["generated_text"]
+    return story_text
+
+# text2audio
+def text2audio(story_text):
+    text2audio_model = pipeline("text-to-speech", model="Matthijs/mms-tts-eng")
+    gen_audio = text2audio_model(story_text)
+    return gen_audio
+
+def main():
+    st.set_page_config(page_title="Your Image to Audio Story",page_icon="🦜")
+    st.header("Turn Your Image to Audio Story")
+    uploaded_file = st.file_uploader("Select an Image...")
+    
+    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_container_width=True)
+    
+        # #Stage 1: Image to Text
+        st.text('Processing img2text...')
+        scenario = img2text(uploaded_file.name)
+        st.write(scenario)
+    
+        # #Stage 2: Text to Story
+        st.text('Generating a story...')
+        story = text2story(scenario)
+        st.write(story)
+    
+        #Stage 3: Story to Audio data
+        st.text('Generating audio data...')
+        audio_data =text2audio(story)
+    
+        # Play button
+        if st.button("Play Audio"):
+            # st.audio(audio_data['audio'], sample_rate = audio_data['sampling_rate'])
+            st.audio(audio_data['audio'],
+                       format="audio/wav",
+                       start_time=0,
+                       sample_rate = audio_data['sampling_rate'])
+            # st.audio("kids_playing_audio.wav")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers
+torch