Create app.py

app.py

@@ -0,0 +1,131 @@
+import gradio as gr
+import numpy as np
+import scipy.signal as signal
+import librosa
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+
+def run_forensic_analysis(vocal_file, master_file):
+    if not vocal_file or not master_file:
+        return None, None, None, "❌ Error: Please upload both assets to run diagnostics."
+    
+    # Load audio clips (Optimized downsampling & 60-second execution cap)
+    y_v, sr_v = librosa.load(vocal_file, sr=22050, duration=60.0)
+    y_m, sr_m = librosa.load(master_file, sr=22050, duration=60.0)
+    
+    # =================================================================
+    # MODULE 1: STRUCTURAL RECURRENCE MAPPER (SSM)
+    # =================================================================
+    # Extract chroma features to map harmonic patterns
+    chroma = librosa.feature.chroma_stft(y=y_m, sr=sr_m, hop_length=1024)
+    chroma = librosa.util.normalize(chroma, axis=0)
+    ssm = np.dot(chroma.T, chroma)
+    
+    fig_ssm = go.Figure(data=gr.Plot(go.Heatmap(
+        z=ssm, colorscale='Viridis', showscale=False,
+        x0=0, dx=1024/sr_m, y0=0, dy=1024/sr_m
+    )))
+    fig_ssm.update_layout(
+        title="Structural Recurrence Matrix (Pattern Matches Over Time)",
+        xaxis_title="Timeline (Seconds)",
+        yaxis_title="Timeline (Seconds)",
+        height=400, margin=dict(l=10, r=10, t=40, b=10)
+    )
+    
+    # =================================================================
+    # MODULE 2: MIX FORENSICS & FREQUENCY HEALTH
+    # =================================================================
+    centroid = librosa.feature.spectral_centroid(y=y_m, sr=sr_m, hop_length=512)[0]
+    flatness = librosa.feature.spectral_flatness(y=y_m, hop_length=512)[0]
+    t_m = librosa.times_like(centroid, sr=sr_m, hop_length=512)
+    
+    rms_m = librosa.feature.rms(y=y_m)[0]
+    crest_factor = np.max(np.abs(y_m)) / (np.mean(rms_m) + 1e-6)
+    
+    fig_mix = make_subplots(rows=2, cols=1, shared_xaxes=True, vertical_spacing=0.1)
+    fig_mix.add_trace(go.Scatter(x=t_m, y=centroid, mode='lines', name='Centroid (Brightness)', line=dict(color='#FF4B4B')), row=1, col=1)
+    fig_mix.add_trace(go.Scatter(x=t_m, y=flatness, mode='lines', name='Flatness (Noise/Harsh)', line=dict(color='#00E5FF')), row=2, col=1)
+    
+    fig_mix.update_layout(
+        title="Spectral Diagnostic Vectors",
+        xaxis2_title="Timeline (Seconds)",
+        height=400, showlegend=False, margin=dict(l=10, r=10, t=40, b=10)
+    )
+    
+    # =================================================================
+    # MODULE 3: SYLLABLE VELOCITY & PHRASING DENSITY
+    # =================================================================
+    onset_v = librosa.onset.onset_strength(y=y_v, sr=sr_v, hop_length=512)
+    t_v = librosa.times_like(onset_v, sr=sr_v, hop_length=512)
+    
+    peaks, _ = signal.find_peaks(onset_v, height=0.2, distance=10)
+    peak_times = t_v[peaks]
+    
+    # Calculate local density (syllables per second window)
+    window_sz = 2.0
+    density_y = []
+    for t in t_v:
+        count = np.sum((peak_times >= t - window_sz/2) & (peak_times <= t + window_sz/2))
+        density_y.append(count / window_sz)
+        
+    fig_vocal = go.Figure()
+    fig_vocal.add_trace(go.Scatter(x=t_v, y=density_y, mode='lines', fill='tozeroy', line=dict(color='#00FF66', width=2)))
+    fig_vocal.update_layout(
+        title="Lyrical Delivery Velocity (Syllables Per Second)",
+        xaxis_title="Timeline (Seconds)",
+        yaxis_title="Syllables/Sec",
+        height=350, margin=dict(l=10, r=10, t=40, b=10)
+    )
+    
+    # =================================================================
+    # DIAGNOSTIC SUMMARY GENERATOR
+    # =================================================================
+    avg_flatness = np.mean(flatness)
+    mix_critique = "Balanced clean spectrum." if avg_flatness < 0.01 else "High harshness/noise ratios detected."
+    if crest_factor > 5.0:
+        dynamics_status = "Dynamic, punchy transient preservation."
+    else:
+        dynamics_status = "Highly compressed / squashed brickwall mix."
+        
+    report = f"""### 📊 Forensic Lab Insights (First 60s)
+* **Dynamic Crest Factor:** {crest_factor:.2f} $\\rightarrow$ *{dynamics_status}*
+* **Total Vocal Artifact Onsets:** {len(peaks)} individual syllables mapped.
+* **Peak Delivery Speed:** {max(density_y):.1f} syllables per second.
+* **Acoustic Blueprint Profile:** {mix_critique}
+
+> **How to interpret charts:** > * **Recurrence Map:** Look for solid diagonal block shapes. These explicitly flag identical choruses or looping sample patterns.
+> * **Spectral Vectors:** Sharp dips or valleys reveal filtering tricks, transitions, or frequency drops.
+> * **Delivery Velocity:** Waves illustrate the emotional phrasing of a performance, showing where the artist rushes or drags words."""
+    
+    return fig_ssm, fig_mix, fig_vocal, report
+
+# =====================================================================
+# INTERFACE LAYOUT
+# =====================================================================
+with gr.Blocks(title="Audio Forensic Analytics Lab") as demo:
+    gr.Markdown("# 🔬 Audio Forensic & Structural Intelligence Lab")
+    gr.Markdown("Drop clean stems extracted from Space 1 to extract advanced frequency blueprints, structural maps, and vocal data matrices.")
+    
+    with gr.Row():
+        vocal_input = gr.Audio(type="filepath", label="Upload Isolated Vocal Stem (vocals.wav)")
+        master_input = gr.Audio(type="filepath", label="Upload Instrumental or Full Mix Master")
+        
+    analyze_btn = gr.Button("Deploy Forensic Diagnosis Engines", variant="primary")
+    
+    with gr.Tab("1. Structural Recurrence Map"):
+        plot_ssm = gr.Plot()
+    with gr.Tab("2. Mix Health & Spectral Vectors"):
+        plot_mix = gr.Plot()
+    with gr.Tab("3. Lyrical Velocity Matrix"):
+        plot_vocal = gr.Plot()
+        
+    text_report = gr.Markdown()
+    
+    analyze_btn.click(
+        fn=run_forensic_analysis,
+        inputs=[vocal_input, master_input],
+        outputs=[plot_ssm, plot_mix, plot_vocal, text_report]
+    )
+
+if __name__ == "__main__":
+    demo.launch()