Create app.py

app.py

@@ -0,0 +1,77 @@
+import streamlit as st
+import tensorflow as tf
+import numpy as np
+import librosa
+import matplotlib.pyplot as plt
+import librosa.display
+import tempfile
+import os
+
+# Load the trained model
+@st.cache_resource
+def load_model():
+    model_path = "sound_classification_model.h5"  # Replace with the path to your .h5 file
+    model = tf.keras.models.load_model(model_path)
+    return model
+
+model = load_model()
+
+# Preprocess audio into a spectrogram
+def preprocess_audio(file_path, n_mels=128, fixed_time_steps=128):
+    try:
+        y, sr = librosa.load(file_path, sr=None)
+        mel_spectrogram = librosa.feature.melspectrogram(y=y, sr=sr, n_mels=n_mels, fmax=sr/2)
+        log_spectrogram = librosa.power_to_db(mel_spectrogram, ref=np.max)
+        log_spectrogram = log_spectrogram / np.max(np.abs(log_spectrogram))
+        if log_spectrogram.shape[1] < fixed_time_steps:
+            padding = fixed_time_steps - log_spectrogram.shape[1]
+            log_spectrogram = np.pad(log_spectrogram, ((0, 0), (0, padding)), mode='constant')
+        else:
+            log_spectrogram = log_spectrogram[:, :fixed_time_steps]
+        return np.expand_dims(log_spectrogram, axis=-1)  # Add channel dimension for CNNs
+    except Exception as e:
+        print(f"Error processing {file_path}: {e}")
+        return None
+
+# Streamlit app UI
+st.title("Audio Spectrogram Prediction")
+st.write("Upload an audio file to generate a spectrogram and predict its class using your trained model.")
+
+# File upload widget
+uploaded_file = st.file_uploader("Choose an audio file", type=["wav", "mp3"])
+
+if uploaded_file is not None:
+    # Save the uploaded audio file to a temporary location
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_audio_file:
+        temp_audio_file.write(uploaded_file.read())
+        temp_audio_path = temp_audio_file.name
+
+    # Preprocess the audio into a spectrogram
+    st.write("Processing audio into a spectrogram...")
+    spectrogram = preprocess_audio(temp_audio_path)
+    
+    if spectrogram is not None:
+        # Display the spectrogram
+        st.write("Generated Spectrogram:")
+        plt.figure(figsize=(10, 4))
+        librosa.display.specshow(spectrogram[:, :, 0], sr=22050, x_axis='time', y_axis='mel', fmax=8000, cmap='plasma')
+        plt.colorbar(format='%+2.0f dB')
+        plt.title('Mel-Spectrogram')
+        plt.tight_layout()
+        st.pyplot(plt)
+
+        # Predict using the model
+        st.write("Predicting...")
+        spectrogram = np.expand_dims(spectrogram, axis=0)  # Add batch dimension
+        predictions = model.predict(spectrogram)
+        predicted_class = np.argmax(predictions, axis=-1)  # Assuming classification
+
+        # Display the results
+        st.write("Prediction Results:")
+        st.write(f"Predicted Class: {int(predicted_class[0])}")
+        st.write(f"Raw Model Output: {predictions}")
+    else:
+        st.write("Failed to process the audio file. Please try again with a different file.")
+
+    # Optional: Clean up temporary file
+    os.remove(temp_audio_path)