Update app.py

app.py

@@ -10,6 +10,10 @@ import io
 import matplotlib.pyplot as plt
 import librosa.display
 from PIL import Image  # For image conversion
+import sqlite3
+import uuid
+import shutil
+from datetime import datetime
 
 # Try to import noisereduce (if not available, noise reduction will be skipped)
 try:
@@ -35,6 +39,37 @@ def add_emoji_to_label(label):
     emoji = emotion_to_emoji.get(label.lower(), "")
     return f"{label.capitalize()} {emoji}"
 
+# Set up SQLite database connection and create table if it doesn't exist.
+conn = sqlite3.connect("predictions.db", check_same_thread=False)
+cursor = conn.cursor()
+cursor.execute('''
+CREATE TABLE IF NOT EXISTS predictions (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    file_path TEXT NOT NULL,
+    predicted_emotion TEXT NOT NULL,
+    timestamp TEXT NOT NULL
+)
+''')
+conn.commit()
+
+def store_prediction(file_path, predicted_emotion):
+    """Store the audio file path, predicted emotion, and current timestamp in the database."""
+    timestamp = datetime.now().isoformat()
+    cursor.execute("INSERT INTO predictions (file_path, predicted_emotion, timestamp) VALUES (?, ?, ?)",
+                   (file_path, predicted_emotion, timestamp))
+    conn.commit()
+
+def save_uploaded_audio(audio_file_path):
+    """Copy the uploaded audio file to a permanent 'uploads' directory with a unique filename."""
+    uploads_dir = "uploads"
+    if not os.path.exists(uploads_dir):
+        os.makedirs(uploads_dir)
+    file_extension = os.path.splitext(audio_file_path)[1]
+    new_filename = f"{uuid.uuid4()}{file_extension}"
+    destination = os.path.join(uploads_dir, new_filename)
+    shutil.copy(audio_file_path, destination)
+    return destination
+
 # Load the pre-trained SpeechBrain classifier
 classifier = foreign_class(
     source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP",
@@ -110,7 +145,7 @@ def predict_emotion(audio_file, use_ensemble=False, apply_noise_reduction=False,
             result = classifier.classify_file(temp_file)
             os.remove(temp_file)
             if isinstance(result, tuple) and len(result) > 3:
-                label = result[3][0]  # Extract predicted emotion label from the tuple
+                label = result[3][0]  # Extract predicted emotion label
             else:
                 label = str(result)
         return add_emoji_to_label(label.lower())
@@ -134,10 +169,14 @@ def plot_waveform(audio_file):
 def predict_and_plot(audio_file, use_ensemble, apply_noise_reduction, segment_duration, overlap):
     """
     Run emotion prediction and generate a waveform plot.
+    Then, save the uploaded audio file and store its metadata in the database.
     Returns a tuple: (emotion label with emoji, waveform image as a PIL Image).
     """
     emotion = predict_emotion(audio_file, use_ensemble, apply_noise_reduction, segment_duration, overlap)
     waveform = plot_waveform(audio_file)
+    # Save the uploaded audio file permanently and store the prediction in the database.
+    stored_file_path = save_uploaded_audio(audio_file)
+    store_prediction(stored_file_path, emotion)
     return emotion, waveform
 
 with gr.Blocks(css=".gradio-container {background-color: #f7f7f7; font-family: Arial;}") as demo:
@@ -145,7 +184,7 @@ with gr.Blocks(css=".gradio-container {background-color: #f7f7f7; font-family: A
     gr.Markdown(
         "Upload an audio file, and the model will predict the emotion using a wav2vec2 model fine-tuned on IEMOCAP data. "
         "The prediction is accompanied by an emoji in the output, and you can also view the audio's waveform. "
-        "Use the options below to adjust ensemble prediction and noise reduction settings."
+        "Your audio file and predicted emotion will be stored locally."
     )
     
     with gr.Tabs():
@@ -177,6 +216,7 @@ with gr.Blocks(css=".gradio-container {background-color: #f7f7f7; font-family: A
   - Optional Noise Reduction.
   - Visualization of the audio waveform.
   - Emoji representation of the predicted emotion in the output.
+  - Local storage of audio files and metadata (predicted emotion, timestamp).
 
 **Credits:**
 - [SpeechBrain](https://speechbrain.github.io)