app.py

import gradio as gr
import tensorflow as tf
import librosa
import numpy as np
from PIL import Image
import requests
from io import BytesIO

# Load model - added caching
model = tf.keras.models.load_model("animal_sound_cnn.h5", compile=False)

# Updated class mapping
class_names = {
    0: "Lion", 1: "Donkey", 2: "Cow", 3: "Cat", 4: "Dog",
    5: "Sheep", 6: "Frog", 7: "Bird", 8: "Monkey", 9: "Chicken"
}

# Fixed image URLs with working links
# Updated reliable image URLs
# Fully working image URLs
import gradio as gr
import numpy as np
from PIL import Image
import requests
from io import BytesIO

# Working image URLs
image_urls = {
    "Lion": "https://upload.wikimedia.org/wikipedia/commons/7/73/Lion_waiting_in_Namibia.jpg",
    "Donkey": "https://upload.wikimedia.org/wikipedia/commons/8/85/%C3%82ne_d%27Ethiopie.jpg",
    "Cow": "https://upload.wikimedia.org/wikipedia/commons/0/0c/Cow_female_black_white.jpg",
    "Cat": "https://upload.wikimedia.org/wikipedia/commons/6/6e/Black_and_white_cat_on_rug.jpg",
    "Dog": "https://upload.wikimedia.org/wikipedia/commons/d/db/Heterochromia_dog%2C_Struga.jpg",
    "Sheep": "https://upload.wikimedia.org/wikipedia/commons/2/2c/Flock_of_sheep.jpg",
    "Frog": "https://upload.wikimedia.org/wikipedia/commons/c/cb/The_Green_and_Golden_Bell_Frog.jpg",
    "Bird": "https://upload.wikimedia.org/wikipedia/commons/f/fb/Brown_thrasher_in_CP_%2802147%29.jpg",
    "Monkey": "https://upload.wikimedia.org/wikipedia/commons/c/c8/Monkey_eating.jpg",
    "Chicken": "https://upload.wikimedia.org/wikipedia/commons/b/b2/Gallus_gallus_domesticus_487567856.jpg"
}

def download_image(url):
    """Download and resize image, with reliable request headers"""
    try:
        headers = {"User-Agent": "Mozilla/5.0"}
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        img = Image.open(BytesIO(response.content)).convert("RGB")
        img = img.resize((300, 300))
        return np.array(img)
    except Exception as e:
        print(f"Image download failed: {e}")
        return np.full((300, 300, 3), 128, dtype=np.uint8)  # gray



def preprocess(audio_path):
    """Audio preprocessing with error handling"""
    try:
        y, sr = librosa.load(audio_path, sr=22050, duration=3)  # Limit to 3s
        mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=40)
        mfcc_mean = np.mean(mfcc, axis=1)
        return mfcc_mean.reshape(1, 40, 1, 1).astype(np.float32)
    except Exception as e:
        raise ValueError(f"Audio processing error: {str(e)}")

def predict(audio_path):
    try:
        # Preprocess audio
        X = preprocess(audio_path)
        
        # Make prediction
        pred = model.predict(X, verbose=0)  # Disable verbose output
        class_id = np.argmax(pred)
        confidence = pred[0][class_id]
        class_name = class_names.get(class_id, f"Unknown ({class_id})")
        
        # Get image
        img = download_image(image_urls.get(class_name, ""))
        
        # Format output
        text_output = (f"Predicted animal: {class_name}\n"
                      f"Confidence: {confidence*100:.2f}%")
        return text_output, img
    
    except Exception as e:
        return f"Error: {str(e)}", download_image("")  # Return error with blank image

# Create interface
with gr.Blocks() as demo:
    gr.Markdown("# 🐾 Animal Sound Classifier")
    gr.Markdown("Upload an animal sound (3-5 seconds) to identify the animal")
    
    with gr.Row():
        audio_input = gr.Audio(
            sources=["upload", "microphone"],
            type="filepath",
            label="Animal Sound",
            max_length=5  # Limit recording to 5 seconds
        )
        
    btn = gr.Button("Identify Animal", variant="primary")
    
    with gr.Row():
        text_output = gr.Textbox(label="Prediction Result", interactive=False)
        image_output = gr.Image(label="Animal Image", height=300)
    
    btn.click(
        fn=predict,
        inputs=audio_input,
        outputs=[text_output, image_output]
    )
    
    gr.Examples(
        examples=[
            ["examples/lion_roar.wav"],
            ["examples/dog_bark.wav"],
            ["examples/bird_chirp.wav"]
        ],
        inputs=audio_input,
        outputs=[text_output, image_output],
        fn=predict,
        cache_examples=True
    )

# Launch with error display enabled
demo.launch(show_error=True)