Update main .py

main .py

@@ -32,9 +32,14 @@ from gtts import gTTS
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
 
-# Download NLTK resources
-nltk.download('punkt')
-nltk.download('stopwords')
+# Set NLTK data path to persistent storage
+nltk.data.path.append('/data/nltk_data')
+# Download NLTK resources if not already present
+try:
+    nltk.download('punkt', download_dir='/data/nltk_data')
+    nltk.download('stopwords', download_dir='/data/nltk_data')
+except Exception as e:
+    print(f"Failed to download NLTK data: {e}")
 
 # Check GPU availability
 print("Checking GPU availability...")
@@ -44,9 +49,14 @@ if torch.cuda.is_available():
 else:
     print("Device set to use CPU")
 
+# Create file storage directory
+os.makedirs('/data/files', exist_ok=True)
+if not os.access('/data/files', os.W_OK):
+    raise PermissionError("No write permission for /data/files directory")
+
 # Initialize SQLite database
 def init_sqlite_db():
-    os.makedirs('/data', exist_ok=True)  # Create /data/ directory if it doesn't exist
+    os.makedirs('/data', exist_ok=True)
     if not os.access('/data', os.W_OK):
         raise PermissionError("No write permission for /data directory")
     conn = sqlite3.connect('/data/vernacular_learning.db')
@@ -118,9 +128,6 @@ def init_sqlite_db():
     conn.commit()
     return conn
 
-# Create file storage directory
-os.makedirs('/content/files', exist_ok=True)
-
 # Define supported languages
 SUPPORTED_LANGUAGES = {
     "Hindi": "hi",
@@ -428,6 +435,20 @@ def get_forum_messages():
     conn.close()
     return messages
 
+def generate_content_tts(content_output, language):
+    if not content_output or "Error" in content_output:
+        return None
+    summary = content_output.split("Summary: ")[-1].split("\n")[0]
+    output_file = f"/data/files/tts_{uuid.uuid4()}.mp3"
+    lang_code = SUPPORTED_LANGUAGES.get(language, 'en')
+    return generate_tts(summary, lang_code, output_file)
+
+def download_content(content_output):
+    if not content_output or "Error" in content_output:
+        return None
+    output_file = f"/data/files/content_{uuid.uuid4()}.pdf"
+    return generate_pdf(content_output, output_file)
+
 def create_gradio_interface():
     with gr.Blocks(theme='default') as interface:
         gr.Markdown("# 🌍 Vernacular Learning Platform")
@@ -511,20 +532,6 @@ def create_gradio_interface():
                     store_content(source, translated_text, language, category, subcategory)
                     return f"Content processed:\nSummary: {summary}\nStored in database."
 
-                def generate_content_tts(content_output, language):
-                    if not content_output or "Error" in content_output:
-                        return None
-                    summary = content_output.split("Summary: ")[-1].split("\n")[0]
-                    output_file = f"/content/files/tts_{uuid.uuid4()}.mp3"
-                    lang_code = SUPPORTED_LANGUAGES.get(language, 'en')
-                    return generate_tts(summary, lang_code, output_file)
-
-                def download_content(content_output):
-                    if not content_output or "Error" in content_output:
-                        return None
-                    output_file = f"/content/files/content_{uuid.uuid4()}.pdf"
-                    return generate_pdf(content_output, output_file)
-
                 process_button.click(
                     fn=process_content,
                     inputs=[content_type, pdf_input, url_input, language, category, subcategory],