Update app.py

app.py

@@ -1,40 +1,32 @@
 import streamlit as st
-from diffusers import DiffusionPipeline
+from transformers import pipeline
 
-# Load the Diffusion pipeline
-@st.cache_data(allow_output_mutation=True)
-def load_diffusion_pipeline():
-    try:
-        pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium")
-        return pipeline
-    except Exception as e:
-        st.error(f"Error loading model: {e}")
+# Load the audio classification pipeline
+audio_classification_pipeline = pipeline("audio-classification", model="MIT/ast-finetuned-audioset-10-10-0.4593")
 
-def generate_response(prompt_text, pipeline):
-    try:
-        response = pipeline(prompt_text, top_p=0.9, max_length=100)[0]['generated_text']
-        return response
-    except Exception as e:
-        st.error(f"Error generating response: {e}")
+def classify_audio(audio_file):
+    # Perform audio classification
+    results = audio_classification_pipeline(audio=audio_file)
+    return results
 
 def main():
-    st.title('Hugging Face Diffusion Model')
+    st.title('Hugging Face Audio Classification')
 
-    # Load the model
-    pipeline = load_diffusion_pipeline()
+    # File uploader for audio file
+    st.subheader('Upload Audio File:')
+    audio_file = st.file_uploader("Choose a WAV file", type=["wav"])
 
-    # Text input for the prompt
-    prompt_text = st.text_area("Enter your prompt here:", height=200)
+    # Check if audio file is uploaded
+    if audio_file is not None:
+        st.audio(audio_file, format='audio/wav')
 
-    # Button to generate prompt
-    if st.button("Generate"):
-        if prompt_text:
-            with st.spinner('Generating...'):
-                generated_text = generate_response(prompt_text, pipeline)
-            st.success('Generation complete!')
-            st.text_area('Generated Text:', value=generated_text, height=400)
-        else:
-            st.warning('Please enter a prompt.')
+        # Button to classify audio
+        if st.button('Classify'):
+            with st.spinner('Classifying...'):
+                # Perform classification
+                results = classify_audio(audio_file)
+            st.success('Classification complete!')
+            st.write("Prediction:", results)
 
 if __name__ == '__main__':
     main()