Update app.py

app.py

@@ -10,7 +10,7 @@ import soundfile as sf
 import matplotlib.pyplot as plt
 import scipy.signal as sps
 
-# Local modules
+# Local Modules
 from io_utils import read_audio_info
 from time_domain import compute_time_domain_stats
 from spectral import compute_spectral_analysis
@@ -25,90 +25,90 @@ from report_generator import create_report
 # ============================================================
 
 def analyze_audio(audio_file, progress=gr.Progress()):
-    """Full forensic audio analysis pipeline."""
-
     if audio_file is None:
         return None, "⚠️ Please upload an audio file."
 
     try:
         path = Path(audio_file)
 
-        # -----------------------------
+        # ------------------------------------------------------
         # FILE INFO + LOAD AUDIO
-        # -----------------------------
-        progress(0.10, desc="Reading file info...")
+        # ------------------------------------------------------
+        progress(0.10, desc="Reading file...")
         info = read_audio_info(str(path))
 
         progress(0.25, desc="Loading waveform...")
         y, sr = librosa.load(str(path), sr=None, mono=True)
 
-        # -----------------------------
-        # TIME DOMAIN
-        # -----------------------------
+        # ------------------------------------------------------
+        # TIME-DOMAIN ANALYSIS
+        # ------------------------------------------------------
         progress(0.35, desc="Time-domain analysis...")
         time_stats = compute_time_domain_stats(y)
 
-        # -----------------------------
+        # ------------------------------------------------------
         # SPECTRAL ANALYSIS
-        # -----------------------------
+        # ------------------------------------------------------
         progress(0.50, desc="Spectral analysis...")
         spectral = compute_spectral_analysis(y, sr)
 
-        # -----------------------------
+        # ------------------------------------------------------
         # LOUDNESS
-        # -----------------------------
-        progress(0.60, desc="Computing loudness...")
+        # ------------------------------------------------------
+        progress(0.60, desc="Computing LUFS loudness...")
         lufs = compute_loudness(y, sr) if LOUDNESS_AVAILABLE else None
 
-        # -----------------------------
+        # ------------------------------------------------------
         # ISSUE DETECTION
-        # -----------------------------
-        progress(0.70, desc="Detecting anomalies...")
+        # ------------------------------------------------------
+        progress(0.70, desc="Detecting spectral & time issues...")
         issues = detect_audio_issues(spectral, time_stats)
 
-        # -----------------------------
-        # SYNTHETIC VOICE (INFO ONLY)
-        # -----------------------------
-        progress(0.78, desc="Synthetic voice estimation...")
+        # ------------------------------------------------------
+        # SYNTHETIC VOICE ESTIMATION (INFO ONLY)
+        # ------------------------------------------------------
+        progress(0.78, desc="Synthetic voice probability...")
         synthetic = detect_synthetic_voice(y, sr, spectral)
 
         # ======================================================
-        # SCORING — CLEAN VERSION (NO DUPLICATE ASSIGNMENT)
+        # SCORING SYSTEM (FINAL, CLEAN VERSION)
         # ======================================================
-        progress(0.82, desc="Scoring...")
+        progress(0.82, desc="Scoring audio quality...")
 
         critical = sum(1 for _, sev, _ in issues if sev == "CRITICAL")
-        high = sum(1 for _, sev, _ in issues if sev == "HIGH")
-        medium = sum(1 for _, sev, _ in issues if sev == "MEDIUM")
-        low = sum(1 for _, sev, _ in issues if sev == "LOW")
+        high     = sum(1 for _, sev, _ in issues if sev == "HIGH")
+        medium   = sum(1 for _, sev, _ in issues if sev == "MEDIUM")
+        low      = sum(1 for _, sev, _ in issues if sev == "LOW")
 
         score_value = 100 - (critical * 30) - (high * 15) - (medium * 5)
         score_value = max(0, score_value)
 
+        # SAFE, MATPLOTLIB-COMPATIBLE COLORS
         if score_value >= 90:
             grade, quality = "A", "EXCELLENT"
-            color = "#b3ffb3"
+            color = "#b3ffb3"   # soft green
             recommendation = "Excellent for TTS dataset"
         elif score_value >= 75:
             grade, quality = "B", "GOOD"
             color = "#ccffcc"
-            recommendation = "Very good quality; suitable for TTS"
+            recommendation = "Good quality; suitable for TTS"
         elif score_value >= 60:
             grade, quality = "C", "FAIR"
             color = "#fff6b3"
-            recommendation = "Usable but may contain processing artifacts"
+            recommendation = "Fair; contains noticeable processing artifacts"
         elif score_value >= 40:
             grade, quality = "D", "POOR"
             color = "#ffd9b3"
-            recommendation = "Not recommended for TTS (heavy processing)"
+            recommendation = "Poor quality; not recommended for TTS"
         else:
             grade, quality = "F", "CRITICAL"
             color = "#ffb3b3"
-            recommendation = "Severely degraded or processed; avoid for TTS"
+            recommendation = "Severely degraded or heavily processed audio"
 
         cleanliness_score = max(0, 100 - (medium * 5 + low * 3))
         processing_severity = (critical * 3) + (high * 2) + medium
 
+        # Score Dictionary
         score_dict = {
             "score": score_value,
             "grade": grade,
@@ -124,7 +124,7 @@ def analyze_audio(audio_file, progress=gr.Progress()):
         }
 
         # ======================================================
-        # BUILD FINAL AUDIO_DATA PAYLOAD (SAFE ORDER)
+        # ASSEMBLE FINAL audio_data PAYLOAD
         # ======================================================
         audio_data = {
             "filename": path.name,
@@ -139,29 +139,27 @@ def analyze_audio(audio_file, progress=gr.Progress()):
         }
 
         # ======================================================
-        # REPORT GENERATION
+        # PNG REPORT GENERATION
         # ======================================================
-        progress(0.92, desc="Rendering PNG report...")
-
-        output_dir = Path("reports")
-        output_dir.mkdir(exist_ok=True)
+        progress(0.92, desc="Rendering PNG forensic report...")
 
-        output_file = output_dir / f"{path.stem}_report.png"
+        report_dir = Path("reports")
+        report_dir.mkdir(exist_ok=True)
+        output_file = report_dir / f"{path.stem}_report.png"
 
         create_report(audio_data, str(output_file))
 
         # ======================================================
-        # MARKDOWN SUMMARY (CORRECTED)
+        # SUMMARY MARKDOWN OUTPUT
         # ======================================================
 
-        progress(1.00, desc="Complete!")
-
         s = score_dict
+        e = spectral["energy_distribution"]
 
         md = f"""
-# 🎵 Audio Forensic Analysis — Summary Report
+# 🎵 Audio Forensic Summary Report
 
-## 📁 File
+## 📁 File Information
 - **Name:** `{audio_data['filename']}`
 - **Duration:** {info['duration']:.2f}s  
 - **Sample Rate:** {info['samplerate']} Hz  
@@ -169,7 +167,21 @@ def analyze_audio(audio_file, progress=gr.Progress()):
 
 ---
 
-## 🧪 Quality Assessment
+## 🎚 Loudness (ITU-R BS.1770-3)
+- **Integrated LUFS:** {lufs:.2f} LUFS  
+"""
+
+        # Loudness Compliance
+        if lufs is not None:
+            if -25 <= lufs <= -21:
+                md += f"  - **Status:** PASS ✅ (Compliant −23 LUFS ±2)\n"
+            else:
+                md += f"  - **Status:** FAIL ❌ (Not compliant with −23 LUFS ±2)\n"
+
+        md += f"""
+---
+
+## 🧪 Audio Quality Score
 - **Score:** {s['score']}/100  
 - **Grade:** {s['grade']}  
 - **Quality:** {s['quality']}  
@@ -177,24 +189,42 @@ def analyze_audio(audio_file, progress=gr.Progress()):
 
 ---
 
-## 🔧 Time-Domain Metrics
+## 🔧 Time-Domain Characteristics
 | Metric | Value |
 |--------|--------|
-| Peak | {time_stats['peak_db']:.2f} dBFS |
-| RMS | {time_stats['rms_db']:.2f} dBFS |
-| Crest | {time_stats['crest_factor_db']:.2f} dB |
+| Peak Level | {time_stats['peak_db']:.2f} dBFS |
+| RMS Level | {time_stats['rms_db']:.2f} dBFS |
+| Crest Factor | {time_stats['crest_factor_db']:.2f} dB |
+| Noise Floor | {time_stats['noise_floor']:.6f} |
 | SNR | {time_stats['snr_db']:.1f} dB |
 | ZCR | {time_stats['zero_crossing_rate']:.4f} |
 
-"""
+---
 
-        if lufs is not None:
-            md += f"- **Integrated LUFS:** {lufs:.2f} LUFS\n"
+## 🎛 Spectral Analysis
+| Parameter | Value |
+|----------|--------|
+| Spectral Centroid | {spectral['spectral_centroid']:.1f} Hz |
+| 85% Rolloff | {spectral['rolloff_85pct']:.1f} Hz |
+| 95% Rolloff | {spectral['rolloff_95pct']:.1f} Hz |
+| Highest Frequency (−60 dB) | {spectral['highest_freq_minus60db']:.1f} Hz |
 
-        md += f"""
 ---
 
-## 🤖 Synthetic Voice (Informational Only)
+## 🔊 Energy Distribution (Speech Frequency Bands)
+| Band | Energy % |
+|------|----------|
+| <100 Hz | {e['below_100hz']:.2f}% |
+| 100–500 Hz | {e['100_500hz']:.2f}% |
+| 500–2k Hz | {e['500_2khz']:.2f}% |
+| 2k–8k Hz | {e['2k_8khz']:.2f}% |
+| 8k–12k Hz | {e['8k_12khz']:.2f}% |
+| 12k–16k Hz | {e['12k_16hz']:.2f}% |
+| >16k Hz | {e['above_16khz']:.2f}% |
+
+---
+
+## 🤖 Synthetic Voice Estimate (For Information Only)
 - **Probability:** {synthetic['synthetic_probability']:.3f}
 - **Label:** {synthetic['synthetic_label']}
 
@@ -204,16 +234,16 @@ def analyze_audio(audio_file, progress=gr.Progress()):
 """
 
         if issues:
-            icon_map = {"CRITICAL": "🔴", "HIGH": "🟠", "MEDIUM": "🟡", "LOW": "🟢"}
+            icons = {"CRITICAL":"🔴","HIGH":"🟠","MEDIUM":"🟡","LOW":"🟢"}
             for issue, sev, desc in issues:
-                md += f"- {icon_map.get(sev,'⚪')} **[{sev}] {issue}** — {desc}\n"
+                md += f"- {icons[sev]} **[{sev}] {issue}** — {desc}\n"
         else:
-            md += "- ✅ No significant issues detected\n"
+            md += "- ✅ No issues detected.\n"
 
         md += f"""
 ---
 
-📊 **PNG Report Saved:** `{output_file.name}`  
+📊 **PNG Forensic Report Saved:** `{output_file.name}`  
 🕒 Generated: {audio_data['timestamp']}
 """
 
@@ -225,6 +255,7 @@ def analyze_audio(audio_file, progress=gr.Progress()):
         return None, f"# ❌ Analysis Failed\n{str(e)}"
 
 
+
 # ============================================================
 # GRADIO UI
 # ============================================================
@@ -232,41 +263,35 @@ def analyze_audio(audio_file, progress=gr.Progress()):
 with gr.Blocks(title="Audio Forensic Analyzer", theme="soft") as demo:
 
     gr.Markdown("""
-# 🎧 Audio Forensic Analyzer
-Upload an audio file to generate a forensic-quality report including:
-- HF/LF analysis  
+# 🎧 AUDIO FORENSIC ANALYZER
+Upload an audio file to generate a **full forensic spectral report**:
+- HF/LF rolloff  
 - Filtering detection (HPF / LPF / Brickwall)  
 - Noise reduction artifacts  
-- Compression indicators  
+- Clipping & compression indicators  
 - Spectral notches  
-- Loudness (LUFS)  
-- Synthetic voice estimation  
-The tool outputs a **PNG forensic report** + **Summary Markdown**.
+- LUFS (ITU-R BS.1770-3)  
+- Synthetic speech probability  
+Outputs a **PNG forensic report + Markdown summary**
 """)
 
     with gr.Row():
         with gr.Column(scale=1):
-            audio_input = gr.Audio(
-                label="📁 Upload Audio",
-                type="filepath"
-            )
-            analyze_button = gr.Button("🔍 Analyze Audio", variant="primary")
+            audio_in = gr.Audio(label="📁 Upload Audio", type="filepath")
+            analyze_btn = gr.Button("🔍 Analyze Audio", variant="primary")
 
         with gr.Column(scale=2):
-            png_output = gr.Image(
-                label="📊 Forensic Report (PNG)",
-                type="filepath",
-                height=600
-            )
+            png_out = gr.Image(label="📊 Forensic PNG Report", type="filepath", height=600)
 
-    summary_output = gr.Markdown(label="📋 Summary Report")
+    summary_out = gr.Markdown(label="📋 Summary Report")
 
-    analyze_button.click(
+    analyze_btn.click(
         fn=analyze_audio,
-        inputs=[audio_input],
-        outputs=[png_output, summary_output]
+        inputs=[audio_in],
+        outputs=[png_out, summary_out]
     )
 
 
+# Run Space
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860, show_error=True)