Update app.py

app.py

@@ -6,13 +6,20 @@ from keybert import KeyBERT
 from fpdf import FPDF
 import os
 
-openai.api_key = os.getenv("OPENAI_API_KEY")  # Set this in HF Space secrets
+# --- SETUP ---
+openai.api_key = os.getenv("OPENAI_API_KEY")  # Set this in your HF Space Secrets
 
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 kw_model = KeyBERT()
-# Sample brand list for detection (customize as needed)
-BRANDS = ["Zerodha", "Motilal", "ICICI", "HDFC", "ShareKhan", "IND Money", "Samsung", "Nike", "Adidas"]
+FONT_PATH = "DejaVuSans.ttf"  # Upload this to your Space!
 
+BRANDS = [
+    "Apple", "Google", "Microsoft", "Amazon", "Coca-Cola", "Pepsi", "Samsung", "Nike", "Adidas",
+    "Meta", "Facebook", "Instagram", "YouTube", "Netflix", "Reliance", "Tata", "Airtel", "Jio",
+    "Infosys", "Wipro", "Paytm", "Zomato", "Swiggy", "OLA", "Uber"
+]
+
+# --- HELPERS ---
 def extract_brands(text):
     found = [brand for brand in BRANDS if brand.lower() in text.lower()]
     return found if found else ["None detected"]
@@ -27,54 +34,58 @@ def make_bullets(summary):
     bullets = [f"- {s.strip()}" for s in sentences if s.strip()]
     return "\n".join(bullets)
 
-def make_str(val):
-    try:
-        if val is None:
-            return ""
-        if isinstance(val, (bool, int, float)):
-            return str(val)
-        if isinstance(val, list):
-            return "\n".join([make_str(v) for v in val])
-        if isinstance(val, dict):
-            return str(val)
-        return str(val)
-    except Exception:
-        return ""
-
+# --- PDF REPORT CREATION ---
 def create_pdf_report(language, transcript, transcript_en, summary, brands, topics, key_takeaways):
     pdf = FPDF()
     pdf.add_page()
-    pdf.set_font("Arial", "B", 16)
+    # Use DejaVu Unicode font (must be uploaded to Space root)
+    pdf.add_font("DejaVu", style="", fname=FONT_PATH, uni=True)
+    pdf.add_font("DejaVu", style="B", fname=FONT_PATH, uni=True)
+    pdf.set_font("DejaVu", "B", 16)
     pdf.cell(0, 10, "Audio Transcript & Analysis Report", ln=True, align="C")
-    pdf.set_font("Arial", size=12)
+    pdf.set_font("DejaVu", size=12)
     pdf.ln(5)
     pdf.cell(0, 10, f"Detected Language: {language}", ln=True)
     pdf.ln(5)
-    pdf.multi_cell(0, 8, "Original Transcript:\n" + transcript)
+    pdf.multi_cell(0, 8, "Original Transcript:\n" + (transcript or ""))
     pdf.ln(3)
-    pdf.multi_cell(0, 8, "English Transcript:\n" + transcript_en)
+    pdf.multi_cell(0, 8, "English Transcript:\n" + (transcript_en or ""))
     pdf.ln(3)
-    pdf.set_font("Arial", "B", 12)
+    pdf.set_font("DejaVu", "B", 12)
     pdf.cell(0, 10, "Brands Detected:", ln=True)
-    pdf.set_font("Arial", size=12)
+    pdf.set_font("DejaVu", size=12)
     pdf.multi_cell(0, 8, ", ".join(brands))
-    pdf.set_font("Arial", "B", 12)
+    pdf.set_font("DejaVu", "B", 12)
     pdf.cell(0, 10, "Key Topics:", ln=True)
-    pdf.set_font("Arial", size=12)
+    pdf.set_font("DejaVu", size=12)
     pdf.multi_cell(0, 8, ", ".join(topics))
-    pdf.set_font("Arial", "B", 12)
+    pdf.set_font("DejaVu", "B", 12)
     pdf.cell(0, 10, "Summary (Bulleted):", ln=True)
-    pdf.set_font("Arial", size=12)
+    pdf.set_font("DejaVu", size=12)
     for takeaway in key_takeaways.split('\n'):
         pdf.multi_cell(0, 8, takeaway)
-    # Save to temporary file
     pdf_file = "/tmp/analysis_report.pdf"
     pdf.output(pdf_file)
     return pdf_file
 
+def make_str(val):
+    try:
+        if val is None:
+            return ""
+        if isinstance(val, (bool, int, float)):
+            return str(val)
+        if isinstance(val, list):
+            return "\n".join([make_str(v) for v in val])
+        if isinstance(val, dict):
+            return str(val)
+        return str(val)
+    except Exception:
+        return ""
+
+# --- MAIN APP FUNCTION ---
 def process_audio(audio_path):
     if not audio_path or not isinstance(audio_path, str):
-        return ("No audio file provided.", "", "", "", "", "", "", None)
+        return ("No audio file provided.", "", "", "", "", "", None)
     try:
         with open(audio_path, "rb") as audio_file:
             transcript = openai.audio.transcriptions.create(
@@ -84,7 +95,7 @@ def process_audio(audio_path):
             )
         transcript = make_str(transcript).strip()
     except Exception as e:
-        return (make_str(f"Error in transcription: {e}"), "", "", "", "", "", "", None)
+        return (f"Error in transcription: {e}", "", "", "", "", "", None)
     try:
         detected_lang = detect(transcript)
         lang_text = {'en': 'English', 'hi': 'Hindi', 'ta': 'Tamil'}.get(detected_lang, detected_lang)
@@ -101,17 +112,17 @@ def process_audio(audio_path):
                 )
             transcript_en = make_str(transcript_en).strip()
         except Exception as e:
-            transcript_en = make_str(f"Error translating: {e}")
+            transcript_en = f"Error translating: {e}"
     try:
         summary_obj = summarizer(transcript_en, max_length=100, min_length=30, do_sample=False)
         summary = summary_obj[0]["summary_text"] if isinstance(summary_obj, list) and "summary_text" in summary_obj[0] else make_str(summary_obj)
     except Exception as e:
-        summary = make_str(f"Error summarizing: {e}")
+        summary = f"Error summarizing: {e}"
     # New: Brands, topics, bullets
     brands = extract_brands(transcript_en)
     topics = extract_topics(transcript_en)
     key_takeaways = make_bullets(summary)
-    # New: PDF file generation
+    # PDF file generation
     pdf_file = create_pdf_report(lang_text, transcript, transcript_en, summary, brands, topics, key_takeaways)
     return (
         lang_text,
@@ -123,6 +134,7 @@ def process_audio(audio_path):
         pdf_file
     )
 
+# --- GRADIO INTERFACE ---
 iface = gr.Interface(
     fn=process_audio,
     inputs=gr.Audio(type="filepath", label="Upload MP3/WAV Audio"),
@@ -135,7 +147,7 @@ iface = gr.Interface(
         gr.Textbox(label="Bulleted Key Takeaways"),
         gr.File(label="Download PDF Report")
     ],
-    title="Audio Transcript, Brand & Topic Analysis (OpenAI Whisper + PDF Download)",
+    title="Audio Transcript, Brand & Topic Analysis (OpenAI Whisper + Unicode PDF Download)",
     description="Upload your audio file (MP3/WAV). Get full transcript, summary, brand and topic detection, and download results as PDF."
 )