Upload 2 files

app.py

@@ -1,30 +1,56 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import pipeline, AutoProcessor, AutoModel
+from scipy.io.wavfile import write as write_wav
+import numpy as np
+import torch
 
-# Load the text classification model pipeline
-classifier = pipeline("text-classification",model='isom5240ust/bert-base-uncased-emotion', return_all_scores=True)
+def img2text(image_path):
+    img2caption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    return img2caption(image_path)[0]['generated_text']
 
-# Streamlit application title
-st.title("Text Classification for you")
-st.write("Classification for 6 emotions: sadness, joy, love, anger, fear, surprise")
+def text2story(text):
+    pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
+    story_text = pipe(text, max_length=100)[0]['generated_text']
+    return story_text
 
-# Text input for user to enter the text to classify
-text = st.text_area("Enter the text to classify", "")
+def text2audio(story_text):
+    processor = AutoProcessor.from_pretrained("facebook/mms-tts-eng")
+    model = AutoModel.from_pretrained("facebook/mms-tts-eng")
 
-# Perform text classification when the user clicks the "Classify" button
-if st.button("Classify"):
-    # Perform text classification on the input text
-    results = classifier(text)[0]
+    inputs = processor(text=story_text, return_tensors="pt")
+    with torch.no_grad():
+        output = model(**inputs).waveform
 
-    # Display the classification result
-    max_score = float('-inf')
-    max_label = ''
+    audio_array = output.cpu().numpy().squeeze()
+    sample_rate = 16000 
 
-    for result in results:
-        if result['score'] > max_score:
-            max_score = result['score']
-            max_label = result['label']
+    return audio_array, sample_rate
 
-    st.write("Text:", text)
-    st.write("Label:", max_label)
-    st.write("Score:", max_score)
+# Streamlit UI
+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:
+    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)
+
+    # 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
+    st.text('Generating audio...')
+    audio_array, sample_rate = text2audio(story)
+    
+    audio_file = "output_audio.wav"
+    write_wav(audio_file, sample_rate, audio_array)
+    st.audio(audio_file)

requirements.txt

@@ -1,3 +1,6 @@
-spaces
+streamlit
 transformers
-torch
+torch
+scipy
+soundfile
+numpy