Upload folder using huggingface_hub

app.py

@@ -81,8 +81,8 @@ from preprocess import process_image_data
 
     # Using the decorator directly on the function definition
 @spaces.GPU
-def predict_sweetness(audio, image, model_path):
-    """Function with GPU acceleration"""
+def predict_ripeness(audio, image, model_path):
+    """Function with GPU acceleration to predict watermelon ripeness"""
     try:
         # Now check CUDA availability inside the GPU-decorated function
         if torch.cuda.is_available():
@@ -192,28 +192,28 @@ def predict_sweetness(audio, image, model_path):
         print(f"\033[92mDEBUG\033[0m: Running inference on device: {device}")
         if mfcc is not None and processed_image is not None:
             with torch.no_grad():
-                sweetness = model(mfcc, processed_image)
-                print(f"\033[92mDEBUG\033[0m: Prediction successful: {sweetness.item()}")
+                ripeness = model(mfcc, processed_image)
+                print(f"\033[92mDEBUG\033[0m: Prediction successful: {ripeness.item()}")
         else:
             return "Error: Failed to process inputs. Please check the debug logs."
         
         # Format the result
-        if sweetness is not None:
-            result = f"Predicted Sweetness: {sweetness.item():.2f}/13"
+        if ripeness is not None:
+            result = f"Predicted Ripeness: {ripeness.item():.2f}/13"
             
             # Add a qualitative description
-            if sweetness.item() < 9:
-                result += "\n\nThis watermelon is not very sweet. You might want to choose another one."
-            elif sweetness.item() < 10:
-                result += "\n\nThis watermelon has moderate sweetness."
-            elif sweetness.item() < 11:
-                result += "\n\nThis watermelon is sweet! A good choice."
+            if ripeness.item() < 9:
+                result += "\n\nThis watermelon is not very ripe. You might want to choose another one."
+            elif ripeness.item() < 10:
+                result += "\n\nThis watermelon has moderate ripeness."
+            elif ripeness.item() < 11:
+                result += "\n\nThis watermelon is ripe! A good choice."
             else:
-                result += "\n\nThis watermelon is very sweet! Excellent choice!"
+                result += "\n\nThis watermelon is perfectly ripe! Excellent choice!"
                 
             return result
         else:
-            return "Error: Could not predict sweetness. Please try again with different inputs."
+            return "Error: Could not predict ripeness. Please try again with different inputs."
     
     except Exception as e:
         import traceback
@@ -229,25 +229,25 @@ def create_app(model_path):
     """Create and launch the Gradio interface"""
     # Define the prediction function with model path
     def predict_fn(audio, image):
-        return predict_sweetness(audio, image, model_path)
+        return predict_ripeness(audio, image, model_path)
     
     # Create Gradio interface
-    with gr.Blocks(title="Watermelon Sweetness Predictor", theme=gr.themes.Soft()) as interface:
-        gr.Markdown("# 🍉 Watermelon Sweetness Predictor")
+    with gr.Blocks(title="Watermelon Ripeness Predictor", theme=gr.themes.Soft()) as interface:
+        gr.Markdown("# 🍉 Watermelon Ripeness Predictor")
         gr.Markdown("""
-        This app predicts the sweetness of a watermelon based on its sound and appearance.
+        This app predicts the ripeness of a watermelon based on its sound and appearance.
         
         ## Instructions:
         1. Upload or record an audio of tapping the watermelon
         2. Upload or capture an image of the watermelon
-        3. Click 'Predict' to get the sweetness estimation
+        3. Click 'Predict' to get the ripeness estimation
         """)
         
         with gr.Row():
             with gr.Column():
                 audio_input = gr.Audio(label="Upload or Record Audio", type="numpy")
                 image_input = gr.Image(label="Upload or Capture Image")
-                submit_btn = gr.Button("Predict Sweetness", variant="primary")
+                submit_btn = gr.Button("Predict Ripeness", variant="primary")
             
             with gr.Column():
                 output = gr.Textbox(label="Prediction Results", lines=6)
@@ -265,7 +265,7 @@ def create_app(model_path):
         - Audio analysis using MFCC features and LSTM neural network
         - Image analysis using ResNet-50 convolutional neural network
         
-        The model was trained on a dataset of watermelons with known sweetness values.
+        The model was trained on a dataset of watermelons with known ripeness values.
         
         ## Tips for best results
         - For audio: Tap the watermelon with your knuckle and record the sound
@@ -277,7 +277,7 @@ def create_app(model_path):
 if __name__ == "__main__":
     import argparse
     
-    parser = argparse.ArgumentParser(description="Watermelon Sweetness Prediction App")
+    parser = argparse.ArgumentParser(description="Watermelon Ripeness Prediction App")
     parser.add_argument(
         "--model_path", 
         type=str,