Update app.py

app.py

@@ -1,30 +1,24 @@
 import streamlit as st
 from transformers import pipeline
 
-# Load the text classification model pipeline
-classifier = pipeline("text-classification", model='isom5240sp24/bert-base-uncased-emotion', return_all_scores=True)
+# 加载 Visual Question Answering 模型
+vqa_pipeline = pipeline("text2text-generation", model="mrm8488/t5-base-finetuned-vqa")
 
-# Streamlit application title
-st.title("Text Classification")
-st.write("Classification for 6 emotions: sadness, joy, love, anger, fear, surprise")
+# 加载文本到语音模型
+text_to_speech_pipeline = pipeline("text-to-speech", model="tts_model_name")
 
-# Text input for user to enter the text to classify
-text = st.text_area("Enter the text to classify", "")
+def main():
+    st.title("Visual Question Answering with Text-to-Speech")
 
-# 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]
+    image_path = st.text_input("Enter image path:")
+    question = st.text_input("Enter your question:")
 
-    # Display the classification result
-    max_score = float('-inf')
-    max_label = ''
+    if st.button("Get Answer"):
+        answer = vqa_pipeline(question, image_path)[0]['generated_text']
+        audio_data = text_to_speech_pipeline(answer)
 
-    for result in results:
-        if result['score'] > max_score:
-            max_score = result['score']
-            max_label = result['label']
-            
-    st.write("Text:", text)
-    st.write("Label:", max_label)
-    st.write("Score:", max_score)
+        st.write("Answer:", answer)
+        st.audio(audio_data[0]["audio"], format='audio/wav')
+
+if __name__ == '__main__':
+    main()