Upload folder using huggingface_hub

app.py

@@ -2,29 +2,29 @@ import gradio as gr
 import re
 from transformers import pipeline
 
-# Load lightweight, fast summarization pipeline
+# Load summarization pipeline safely
+summarizer = None
 try:
     summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
-except Exception as e:
-    summarizer = None
-    print(f"Pipeline loading error: {e}")
+except Exception:
+    try:
+        summarizer = pipeline("text2text-generation", model="sshleifer/distilbart-cnn-12-6")
+    except Exception as e:
+        print(f"Pipeline error: {e}")
 
 def extract_key_points(text, num_points=3):
-    """Extract key sentence points based on sentence length & structure."""
     sentences = [s.strip() for s in re.split(r'(?<=[.!?]) +', text) if len(s.strip()) > 10]
     if not sentences:
         return "• No key sentences identified."
-    # Sort sentences by length/informativeness as simple heuristic
     key_sentences = sorted(sentences, key=lambda s: len(s), reverse=True)[:num_points]
     return "\n".join([f"• {s}" for s in key_sentences])
 
 def analyze_and_summarize(text, max_len, min_len):
-    if not text or len(text.strip()) < 30:
+    if not text or len(text.strip()) < 20:
         return (
-            "⚠️ Please enter a longer text (at least 30 characters) to summarize.",
-            "N/A",
+            "⚠️ Please enter a longer text (at least 20 characters) to summarize.",
             "N/A",
-            "N/A"
+            "### 📊 Summary Analytics\n- Please provide input text."
         )
     
     words_input = len(text.split())
@@ -37,15 +37,16 @@ def analyze_and_summarize(text, max_len, min_len):
                 min_length=int(min_len), 
                 do_sample=False
             )
-            summary_text = summary_res[0]['summary_text']
+            if isinstance(summary_res, list) and len(summary_res) > 0:
+                summary_text = summary_res[0].get('summary_text') or summary_res[0].get('generated_text') or str(summary_res[0])
+            else:
+                summary_text = str(summary_res)
         else:
-            # Fallback heuristic summary if pipeline fails to load
             sentences = [s.strip() for s in re.split(r'(?<=[.!?]) +', text) if len(s.strip()) > 5]
             summary_text = " ".join(sentences[:max(1, len(sentences)//2)])
-    except Exception as err:
-        # Fallback if text is shorter than min_length or another edge case occurs
+    except Exception:
         sentences = [s.strip() for s in re.split(r'(?<=[.!?]) +', text) if len(s.strip()) > 5]
-        summary_text = " ".join(sentences[:2]) if sentences else text
+        summary_text = " ".join(sentences[:2]) if len(sentences) >= 2 else text
 
     words_summary = len(summary_text.split())
     reduction = max(0, round((1 - (words_summary / words_input)) * 100, 1)) if words_input > 0 else 0
@@ -54,12 +55,12 @@ def analyze_and_summarize(text, max_len, min_len):
     key_bullets = extract_key_points(text)
     
     stats_md = f"""
-    ### 📊 Summary Analytics
-    - **Original Word Count**: `{words_input}` words
-    - **Summary Word Count**: `{words_summary}` words
-    - **Text Reduction**: `{reduction}%` smaller
-    - **Est. Reading Time Saved**: `{read_time_saved} minutes`
-    """
+### 📊 Summary Analytics
+- **Original Word Count**: `{words_input}` words
+- **Summary Word Count**: `{words_summary}` words
+- **Text Reduction**: `{reduction}%` smaller
+- **Est. Reading Time Saved**: `{read_time_saved} minutes`
+"""
     
     return summary_text, key_bullets, stats_md
 
@@ -67,7 +68,7 @@ example_1 = """Artificial intelligence (AI) is transforming industries worldwide
 
 example_2 = """Machine learning algorithms build a mathematical model based on sample data, known as training data, to make predictions or decisions without being explicitly programmed to do so. Supervised learning algorithms build a mathematical model of a set of data that contains both the inputs and the desired outputs. Unsupervised learning algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points."""
 
-demo = gr.Blocks(theme=gr.themes.Soft())
+demo = gr.Blocks()
 
 with demo:
     gr.Markdown(