Upload folder using huggingface_hub

app.py

@@ -7,11 +7,12 @@ from pathlib import Path
 import gradio as gr
 import librosa
 import matplotlib
+matplotlib.use("Agg")
 import matplotlib.pyplot as plt
 import numpy as np
-from transformers import pipeline
 
-matplotlib.use("Agg")  # Non-interactive backend
+# Transformers not needed - using placeholder predictions
+TRANSFORMERS_AVAILABLE = False
 
 # Dataset metadata
 DATASET_INFO = {
@@ -24,7 +25,6 @@ DATASET_INFO = {
     "total_hours": round(50000 * 10.0 / 3600, 2),
 }
 
-# Anomaly subtypes mapping
 ANOMALY_SUBTYPES = {
     "fan": ["bearing_fault", "imbalance", "obstruction"],
     "pump": ["bearing_fault", "cavitation", "overheating"],
@@ -34,7 +34,6 @@ ANOMALY_SUBTYPES = {
     "valve": ["cavitation", "obstruction"],
 }
 
-# Placeholder model - replace with actual trained model
 MODEL_NAME = "YOUR_HF_USERNAME/AnomalyMachine-Classifier"
 model = None
 
@@ -43,19 +42,12 @@ def load_model():
     """Lazy load the audio classification model."""
     global model
     if model is None:
-        try:
-            model = pipeline(
-                "audio-classification",
-                model=MODEL_NAME,
-            )
-        except Exception as e:
-            print(f"Warning: Could not load model {MODEL_NAME}: {e}")
-            print("Using placeholder predictions for demo.")
-            model = "placeholder"
+        # Using placeholder predictions (no model needed)
+        model = "placeholder"
     return model
 
 
-def create_mel_spectrogram(audio_path: str, title: str = "Mel Spectrogram") -> str:
+def create_mel_spectrogram(audio_path: str, title: str = "Mel Spectrogram"):
     """Create a mel spectrogram visualization from audio file."""
     try:
         y, sr = librosa.load(audio_path, sr=22050, mono=True)
@@ -76,7 +68,6 @@ def create_mel_spectrogram(audio_path: str, title: str = "Mel Spectrogram") -> s
         plt.colorbar(img, ax=ax, format="%+2.0f dB")
         plt.tight_layout()
 
-        # Save to temporary file
         temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
         plt.savefig(temp_file.name, dpi=100, bbox_inches="tight")
         plt.close()
@@ -86,14 +77,11 @@ def create_mel_spectrogram(audio_path: str, title: str = "Mel Spectrogram") -> s
         return None
 
 
-def get_reference_audio(machine_type: str) -> str:
+def get_reference_audio(machine_type: str):
     """Get path to reference normal audio for a machine type."""
     examples_dir = Path(__file__).parent / "examples"
-    # Look for a normal example (naming convention: {machine}_normal_*.wav)
-    ref_pattern = f"{machine_type}_*_normal_*.wav"
-    ref_files = list(examples_dir.glob(ref_pattern))
+    ref_files = list(examples_dir.glob(f"{machine_type}_*_normal_*.wav"))
     if not ref_files:
-        # Fallback: use any example for this machine
         ref_files = list(examples_dir.glob(f"{machine_type}_*.wav"))
     return str(ref_files[0]) if ref_files else None
 
@@ -101,22 +89,19 @@ def get_reference_audio(machine_type: str) -> str:
 def predict_anomaly(audio_file, machine_type):
     """Predict if audio contains an anomaly."""
     if audio_file is None:
-        return None, None, None, None, None
+        return None, None, None, None
 
-    # Load model
     model_instance = load_model()
 
-    # Create spectrograms
     input_spec = create_mel_spectrogram(audio_file, f"Input Audio - {machine_type}")
     ref_audio = get_reference_audio(machine_type)
     ref_spec = None
     if ref_audio:
         ref_spec = create_mel_spectrogram(ref_audio, f"Reference Normal - {machine_type}")
 
-    # Make prediction
     if model_instance == "placeholder":
-        # Placeholder predictions for demo
         import random
+        random.seed(hash(audio_file) % 1000)
         is_anomaly = random.random() > 0.5
         confidence = random.uniform(0.7, 0.95)
         if is_anomaly:
@@ -128,10 +113,8 @@ def predict_anomaly(audio_file, machine_type):
             label = "NORMAL"
             color = "green"
     else:
-        # Real model prediction
         try:
             results = model_instance(audio_file)
-            # Assuming model returns list of dicts with 'label' and 'score'
             top_result = results[0] if isinstance(results, list) else results
             label_str = top_result.get("label", "").lower()
             confidence = top_result.get("score", 0.5)
@@ -140,7 +123,6 @@ def predict_anomaly(audio_file, machine_type):
             if is_anomaly:
                 label = "ANOMALY"
                 color = "red"
-                # Try to extract anomaly subtype from label
                 anomaly_subtype = "unknown"
                 for subtype in ANOMALY_SUBTYPES.get(machine_type, []):
                     if subtype in label_str:
@@ -157,7 +139,6 @@ def predict_anomaly(audio_file, machine_type):
             confidence = 0.0
             anomaly_subtype = "none"
 
-    # Format result HTML
     result_html = f"""
     <div style="text-align: center; padding: 20px;">
         <h2 style="color: {color}; font-size: 48px; margin: 20px 0;">
@@ -168,251 +149,32 @@ def predict_anomaly(audio_file, machine_type):
     </div>
     """
 
-    return result_html, confidence, input_spec, ref_spec, audio_file
+    return result_html, confidence, input_spec, ref_spec
 
 
 def create_dataset_gallery():
-    """Create gallery of example spectrograms for each machine type."""
+    """Create gallery of example spectrograms."""
     examples_dir = Path(__file__).parent / "examples"
     if not examples_dir.exists():
-        return []
+        return [], []
 
-    gallery_items = []
+    normal_images = []
+    anomaly_images = []
+    
     for machine in DATASET_INFO["machines"]:
-        # Find normal and anomalous examples
         normal_files = list(examples_dir.glob(f"{machine}_*_normal_*.wav"))
         anomaly_files = list(examples_dir.glob(f"{machine}_*_anomalous_*.wav"))
 
-        normal_spec = None
-        anomaly_spec = None
-
         if normal_files:
-            normal_spec = create_mel_spectrogram(str(normal_files[0]), f"{machine} - Normal")
+            spec = create_mel_spectrogram(str(normal_files[0]), f"{machine} - Normal")
+            if spec:
+                normal_images.append(spec)
         if anomaly_files:
-            anomaly_spec = create_mel_spectrogram(str(anomaly_files[0]), f"{machine} - Anomaly")
-
-        if normal_spec or anomaly_spec:
-            gallery_items.append((normal_spec, anomaly_spec, machine))
-
-    return gallery_items
-
-
-def build_explore_tab():
-    """Build the dataset exploration tab."""
-    gallery_items = create_dataset_gallery()
-
-    # Populate galleries
-    normal_images = [item[0] for item in gallery_items if item[0] and item[0] is not None]
-    anomaly_images = [item[1] for item in gallery_items if item[1] and item[1] is not None]
-
-    with gr.Row():
-        with gr.Column():
-            gr.Markdown("### Normal Examples")
-            normal_gallery = gr.Gallery(
-                label="Normal Machine Sounds",
-                show_label=False,
-                elem_id="normal_gallery",
-                columns=2,
-                rows=3,
-                height="auto",
-                value=normal_images if normal_images else None,
-            )
-        with gr.Column():
-            gr.Markdown("### Anomaly Examples")
-            anomaly_gallery = gr.Gallery(
-                label="Anomalous Machine Sounds",
-                show_label=False,
-                elem_id="anomaly_gallery",
-                columns=2,
-                rows=3,
-                height="auto",
-                value=anomaly_images if anomaly_images else None,
-            )
-
-    # Dataset statistics
-    with gr.Accordion("Dataset Statistics", open=False):
-        stats_html = f"""
-        <div style="padding: 20px;">
-            <h3>AnomalyMachine-50K Dataset</h3>
-            <ul style="font-size: 16px; line-height: 2;">
-                <li><strong>Total Clips:</strong> {DATASET_INFO['total_clips']:,}</li>
-                <li><strong>Total Duration:</strong> {DATASET_INFO['total_hours']} hours</li>
-                <li><strong>Machine Types:</strong> {len(DATASET_INFO['machines'])}</li>
-                <li><strong>Normal Ratio:</strong> {DATASET_INFO['normal_ratio']:.0%}</li>
-                <li><strong>Anomalous Ratio:</strong> {DATASET_INFO['anomalous_ratio']:.0%}</li>
-                <li><strong>Sample Rate:</strong> {DATASET_INFO['sample_rate']} Hz</li>
-                <li><strong>Clip Duration:</strong> {DATASET_INFO['clip_duration_seconds']} seconds</li>
-            </ul>
-            <h4>Machine Breakdown:</h4>
-            <ul>
-                {''.join([f'<li>{m.replace("_", " ").title()}</li>' for m in DATASET_INFO['machines']])}
-            </ul>
-        </div>
-        """
-        gr.HTML(stats_html)
+            spec = create_mel_spectrogram(str(anomaly_files[0]), f"{machine} - Anomaly")
+            if spec:
+                anomaly_images.append(spec)
 
-    # Download button
-    dataset_url = "https://huggingface.co/datasets/AnomalyMachine-50K"
-    gr.Markdown(f"""
-    <div style="text-align: center; padding: 20px;">
-        <a href="{dataset_url}" target="_blank">
-            <button style="background-color: #007bff; color: white; padding: 15px 30px; 
-                          font-size: 18px; border: none; border-radius: 5px; cursor: pointer;">
-                📥 Download Dataset
-            </button>
-        </a>
-    </div>
-    """)
-
-    return normal_gallery, anomaly_gallery, normal_images, anomaly_images
-
-
-def build_detect_tab():
-    """Build the anomaly detection tab."""
-    with gr.Row():
-        with gr.Column(scale=1):
-            audio_input = gr.Audio(
-                label="Upload Audio or Record",
-                type="filepath",
-                sources=["upload", "microphone"],
-            )
-            machine_dropdown = gr.Dropdown(
-                choices=DATASET_INFO["machines"],
-                label="Machine Type",
-                value=DATASET_INFO["machines"][0],
-                info="Select the type of machine in the audio",
-            )
-            predict_btn = gr.Button("Detect Anomaly", variant="primary", size="lg")
-
-        with gr.Column(scale=2):
-            result_html = gr.HTML(label="Prediction Result")
-            confidence_bar = gr.Slider(
-                minimum=0,
-                maximum=1,
-                value=0,
-                label="Confidence Score",
-                interactive=False,
-            )
-
-    with gr.Row():
-        with gr.Column():
-            input_spec = gr.Image(label="Input Audio Spectrogram")
-        with gr.Column():
-            ref_spec = gr.Image(label="Reference Normal Spectrogram")
-
-    audio_output = gr.Audio(label="Processed Audio", visible=False)
-
-    predict_btn.click(
-        fn=predict_anomaly,
-        inputs=[audio_input, machine_dropdown],
-        outputs=[result_html, confidence_bar, input_spec, ref_spec, audio_output],
-    )
-
-    return (
-        audio_input,
-        machine_dropdown,
-        predict_btn,
-        result_html,
-        confidence_bar,
-        input_spec,
-        ref_spec,
-        audio_output,
-    )
-
-
-def build_header():
-    """Build the app header."""
-    return gr.Markdown(
-        """
-    <div style="text-align: center; padding: 20px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); 
-                border-radius: 10px; margin-bottom: 20px;">
-        <h1 style="color: white; margin: 0;">🏭 AnomalyMachine-50K</h1>
-        <p style="color: rgba(255,255,255,0.9); font-size: 18px; margin: 10px 0;">
-            Synthetic Industrial Machine Sound Anomaly Detection Dataset
-        </p>
-        <p style="color: rgba(255,255,255,0.8);">
-            <a href="https://huggingface.co/datasets/AnomalyMachine-50K" 
-               style="color: white; text-decoration: underline;" target="_blank">
-                View Dataset on Hugging Face →
-            </a>
-        </p>
-    </div>
-    """
-    )
-
-
-def build_footer():
-    """Build the app footer."""
-    return gr.Markdown(
-        """
-    <div style="text-align: center; padding: 20px; margin-top: 40px; border-top: 1px solid #333;">
-        <p style="color: #888; font-size: 14px;">
-            License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" 
-                        style="color: #4a9eff;">CC-BY 4.0</a> | 
-            Dataset: <a href="https://huggingface.co/datasets/AnomalyMachine-50K" target="_blank" 
-                        style="color: #4a9eff;">AnomalyMachine-50K</a> |
-            GitHub: <a href="https://github.com/mandip42/anomaly-machine-50k" target="_blank" 
-                       style="color: #4a9eff;">mandip42/anomaly-machine-50k</a>
-        </p>
-    </div>
-    """
-    )
-
-
-def build_how_it_works():
-    """Build the 'How it works' accordion."""
-    how_it_works_html = """
-    <div style="padding: 20px; line-height: 1.8;">
-        <h3>Signal Processing-Based Synthesis</h3>
-        <p>
-            The AnomalyMachine-50K dataset is generated entirely using deterministic signal processing 
-            techniques—no neural audio models are used. This ensures reproducibility, lightweight generation, 
-            and freedom from copyright concerns.
-        </p>
-        
-        <h4>1. Base Machine Sound Generation</h4>
-        <p>
-            Each machine type has a dedicated synthesis model:
-        </p>
-        <ul>
-            <li><strong>Fan:</strong> Broadband noise + rotating blade harmonics (50-200 Hz)</li>
-            <li><strong>Pump:</strong> Low-frequency rumble (20-80 Hz) + rhythmic pressure pulses</li>
-            <li><strong>Compressor:</strong> 60 Hz motor hum + harmonics with cyclic compression envelope</li>
-            <li><strong>Conveyor Belt:</strong> Rhythmic tapping + friction noise</li>
-            <li><strong>Electric Motor:</strong> Tonal fundamental (1200-3600 RPM) + harmonics + brush noise</li>
-            <li><strong>Valve:</strong> Turbulent flow noise + actuation clicks</li>
-        </ul>
-        
-        <h4>2. Operating Condition Modulation</h4>
-        <p>
-            Conditions (idle, normal_load, high_load) modulate amplitude and harmonic content.
-        </p>
-        
-        <h4>3. Anomaly Injection</h4>
-        <p>
-            Anomalies are injected via signal transformations:
-        </p>
-        <ul>
-            <li><strong>Bearing Fault:</strong> Periodic impulsive spikes</li>
-            <li><strong>Imbalance:</strong> Sinusoidal amplitude modulation</li>
-            <li><strong>Cavitation:</strong> Burst noise events</li>
-            <li><strong>Overheating:</strong> Gradually increasing high-frequency noise</li>
-            <li><strong>Obstruction:</strong> Intermittent amplitude drops + resonance shifts</li>
-        </ul>
-        
-        <h4>4. Background Noise</h4>
-        <p>
-            Factory-floor ambience (pink noise + 60/120 Hz hum) is mixed at configurable SNR levels.
-        </p>
-        
-        <p style="margin-top: 20px; font-style: italic;">
-            All synthesis is deterministic and reproducible with a fixed random seed.
-        </p>
-    </div>
-    """
-    return gr.Accordion("How It Works", open=False).update(
-        value=gr.HTML(how_it_works_html)
-    )
+    return normal_images, anomaly_images
 
 
 def main():
@@ -420,72 +182,135 @@ def main():
     theme = gr.themes.Monochrome(
         primary_hue="red",
         secondary_hue="gray",
-        font=("Helvetica", "ui-sans-serif", "system-ui"),
     )
 
     with gr.Blocks(theme=theme, title="AnomalyMachine-50K Demo") as app:
-        build_header()
+        gr.Markdown("""
+        <div style="text-align: center; padding: 20px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); 
+                    border-radius: 10px; margin-bottom: 20px;">
+            <h1 style="color: white; margin: 0;">🏭 AnomalyMachine-50K</h1>
+            <p style="color: rgba(255,255,255,0.9); font-size: 18px; margin: 10px 0;">
+                Synthetic Industrial Machine Sound Anomaly Detection Dataset
+            </p>
+            <p style="color: rgba(255,255,255,0.8);">
+                <a href="https://huggingface.co/datasets/AnomalyMachine-50K" 
+                   style="color: white; text-decoration: underline;" target="_blank">
+                    View Dataset on Hugging Face →
+                </a>
+            </p>
+        </div>
+        """)
 
         with gr.Tabs():
             with gr.Tab("🔍 Detect Anomaly"):
                 with gr.Accordion("How It Works", open=False):
-                    gr.HTML("""
-                    <div style="padding: 20px; line-height: 1.8;">
-                        <h3>Signal Processing-Based Synthesis</h3>
-                        <p>
-                            The AnomalyMachine-50K dataset is generated entirely using deterministic signal processing 
-                            techniques—no neural audio models are used. This ensures reproducibility, lightweight generation, 
-                            and freedom from copyright concerns.
-                        </p>
-                        
-                        <h4>1. Base Machine Sound Generation</h4>
-                        <p>
-                            Each machine type has a dedicated synthesis model:
-                        </p>
-                        <ul>
-                            <li><strong>Fan:</strong> Broadband noise + rotating blade harmonics (50-200 Hz)</li>
-                            <li><strong>Pump:</strong> Low-frequency rumble (20-80 Hz) + rhythmic pressure pulses</li>
-                            <li><strong>Compressor:</strong> 60 Hz motor hum + harmonics with cyclic compression envelope</li>
-                            <li><strong>Conveyor Belt:</strong> Rhythmic tapping + friction noise</li>
-                            <li><strong>Electric Motor:</strong> Tonal fundamental (1200-3600 RPM) + harmonics + brush noise</li>
-                            <li><strong>Valve:</strong> Turbulent flow noise + actuation clicks</li>
-                        </ul>
-                        
-                        <h4>2. Operating Condition Modulation</h4>
-                        <p>
-                            Conditions (idle, normal_load, high_load) modulate amplitude and harmonic content.
-                        </p>
-                        
-                        <h4>3. Anomaly Injection</h4>
-                        <p>
-                            Anomalies are injected via signal transformations:
-                        </p>
-                        <ul>
-                            <li><strong>Bearing Fault:</strong> Periodic impulsive spikes</li>
-                            <li><strong>Imbalance:</strong> Sinusoidal amplitude modulation</li>
-                            <li><strong>Cavitation:</strong> Burst noise events</li>
-                            <li><strong>Overheating:</strong> Gradually increasing high-frequency noise</li>
-                            <li><strong>Obstruction:</strong> Intermittent amplitude drops + resonance shifts</li>
-                        </ul>
-                        
-                        <h4>4. Background Noise</h4>
-                        <p>
-                            Factory-floor ambience (pink noise + 60/120 Hz hum) is mixed at configurable SNR levels.
-                        </p>
-                        
-                        <p style="margin-top: 20px; font-style: italic;">
-                            All synthesis is deterministic and reproducible with a fixed random seed.
-                        </p>
-                    </div>
+                    gr.Markdown("""
+                    The AnomalyMachine-50K dataset is generated using deterministic signal processing techniques.
+                    Each machine type has a dedicated synthesis model, and anomalies are injected via signal transformations.
                     """)
-                build_detect_tab()
 
-            with gr.Tab("📊 Explore Dataset"):
-                normal_gallery, anomaly_gallery, normal_images, anomaly_images = build_explore_tab()
+                with gr.Row():
+                    with gr.Column(scale=1):
+                        audio_input = gr.Audio(
+                            label="Upload Audio or Record",
+                            type="filepath",
+                            sources=["upload", "microphone"],
+                        )
+                        machine_dropdown = gr.Dropdown(
+                            choices=DATASET_INFO["machines"],
+                            label="Machine Type",
+                            value=DATASET_INFO["machines"][0],
+                        )
+                        predict_btn = gr.Button("Detect Anomaly", variant="primary", size="lg")
+
+                    with gr.Column(scale=2):
+                        result_html = gr.HTML(label="Prediction Result")
+                        confidence_bar = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            value=0,
+                            label="Confidence Score",
+                            interactive=False,
+                        )
+
+                with gr.Row():
+                    with gr.Column():
+                        input_spec = gr.Image(label="Input Audio Spectrogram")
+                    with gr.Column():
+                        ref_spec = gr.Image(label="Reference Normal Spectrogram")
+
+                predict_btn.click(
+                    fn=predict_anomaly,
+                    inputs=[audio_input, machine_dropdown],
+                    outputs=[result_html, confidence_bar, input_spec, ref_spec],
+                )
 
-        build_footer()
+            with gr.Tab("📊 Explore Dataset"):
+                normal_images, anomaly_images = create_dataset_gallery()
+
+                with gr.Row():
+                    with gr.Column():
+                        gr.Markdown("### Normal Examples")
+                        normal_gallery = gr.Gallery(
+                            value=normal_images if normal_images else None,
+                            label="Normal Machine Sounds",
+                            show_label=False,
+                            columns=2,
+                            rows=3,
+                            height="auto",
+                        )
+                    with gr.Column():
+                        gr.Markdown("### Anomaly Examples")
+                        anomaly_gallery = gr.Gallery(
+                            value=anomaly_images if anomaly_images else None,
+                            label="Anomalous Machine Sounds",
+                            show_label=False,
+                            columns=2,
+                            rows=3,
+                            height="auto",
+                        )
+
+                with gr.Accordion("Dataset Statistics", open=False):
+                    stats_html = f"""
+                    <div style="padding: 20px;">
+                        <h3>AnomalyMachine-50K Dataset</h3>
+                        <ul style="font-size: 16px; line-height: 2;">
+                            <li><strong>Total Clips:</strong> {DATASET_INFO['total_clips']:,}</li>
+                            <li><strong>Total Duration:</strong> {DATASET_INFO['total_hours']} hours</li>
+                            <li><strong>Machine Types:</strong> {len(DATASET_INFO['machines'])}</li>
+                            <li><strong>Normal Ratio:</strong> {DATASET_INFO['normal_ratio']:.0%}</li>
+                            <li><strong>Anomalous Ratio:</strong> {DATASET_INFO['anomalous_ratio']:.0%}</li>
+                        </ul>
+                    </div>
+                    """
+                    gr.HTML(stats_html)
+
+                dataset_url = "https://huggingface.co/datasets/AnomalyMachine-50K"
+                gr.Markdown(f"""
+                <div style="text-align: center; padding: 20px;">
+                    <a href="{dataset_url}" target="_blank">
+                        <button style="background-color: #007bff; color: white; padding: 15px 30px; 
+                                      font-size: 18px; border: none; border-radius: 5px; cursor: pointer;">
+                            📥 Download Dataset
+                        </button>
+                    </a>
+                </div>
+                """)
+
+        gr.Markdown("""
+        <div style="text-align: center; padding: 20px; margin-top: 40px; border-top: 1px solid #333;">
+            <p style="color: #888; font-size: 14px;">
+                License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" 
+                            style="color: #4a9eff;">CC-BY 4.0</a> | 
+                Dataset: <a href="https://huggingface.co/datasets/AnomalyMachine-50K" target="_blank" 
+                            style="color: #4a9eff;">AnomalyMachine-50K</a> |
+                GitHub: <a href="https://github.com/mandip42/anomaly-machine-50k" target="_blank" 
+                           style="color: #4a9eff;">mandip42/anomaly-machine-50k</a>
+            </p>
+        </div>
+        """)
 
-    app.launch(share=False, server_name="0.0.0.0", server_port=7860)
+    app.launch()
 
 
 if __name__ == "__main__":