Create app.py

app.py

@@ -0,0 +1,29 @@
+import streamlit as st
+from transformers import pipeline
+from PIL import Image
+
+# Load pipelines
+image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+text_to_speech = pipeline("text-to-speech", model="facebook/mms-tts-eng")
+
+st.title("Image-to-Text and Text-to-Speech App")
+
+# Image uploader
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
+
+if uploaded_image:
+    image = Image.open(uploaded_image)
+    st.image(image, caption="Uploaded Image", use_container_width=True)
+    
+    # Convert image to text
+    text_output = image_to_text(image)[0]['generated_text']
+    st.write("### Extracted Text:")
+    st.write(text_output)
+    
+    # Convert text to speech
+    speech_output = text_to_speech(text_output)
+    st.write("### Listen to Speech Output:")
+    st.audio(speech_output['audio'], 
+             format="audio/wav", 
+             start_time=0, 
+             sample_rate = speech_output['sampling_rate'])