Create app.py

app.py

@@ -0,0 +1,111 @@
+# app.py
+import streamlit as st
+from transformers import pipeline
+from googletrans import Translator
+from rouge_score import rouge_scorer
+import torch
+
+# -------------------------------
+# Page Config
+# -------------------------------
+st.set_page_config(page_title="Multilingual Summarization Dashboard", layout="wide")
+
+# -------------------------------
+# Style
+# -------------------------------
+with open("style.css") as f:
+    st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
+
+# -------------------------------
+# Model Loading
+# -------------------------------
+@st.cache_resource(show_spinner=True)
+def load_models():
+    models = {}
+    models['urT5-base'] = pipeline(
+        "summarization",
+        model="mbshr/urt5-base-finetuned",
+        device=0 if torch.cuda.is_available() else -1
+    )
+    models['mT5-small'] = pipeline(
+        "summarization",
+        model="google/mt5-small",
+        device=0 if torch.cuda.is_available() else -1
+    )
+    models['mT5-base'] = pipeline(
+        "summarization",
+        model="google/mt5-base",
+        device=0 if torch.cuda.is_available() else -1
+    )
+    return models
+
+models = load_models()
+translator = Translator()
+scorer = rouge_scorer.RougeScorer(['rouge1', 'rouge2', 'rougeL'], use_stemmer=True)
+
+# -------------------------------
+# Sidebar
+# -------------------------------
+st.sidebar.title("Settings")
+selected_model = st.sidebar.selectbox("Choose Summarization Model", list(models.keys()))
+max_length = st.sidebar.slider("Max summary length", 50, 500, 150)
+min_length = st.sidebar.slider("Min summary length", 10, 300, 40)
+target_lang = st.sidebar.selectbox("Translate summary to", ["None", "English", "Urdu", "French", "Spanish"])
+show_comparison = st.sidebar.checkbox("Compare models")
+show_rouge = st.sidebar.checkbox("Show ROUGE Score (requires reference)")
+
+# -------------------------------
+# Main Interface
+# -------------------------------
+st.title("🌐 Multilingual Summarization Dashboard")
+st.write("Enter text to summarize, optionally translate, compare models, and evaluate with ROUGE.")
+
+text = st.text_area("Enter text to summarize:", height=200)
+reference_text = ""
+if show_rouge:
+    reference_text = st.text_area("Reference summary for ROUGE evaluation:", height=100)
+
+# -------------------------------
+# Generate Summary
+# -------------------------------
+if st.button("Generate Summary"):
+    if not text.strip():
+        st.error("Please enter some text!")
+    else:
+        # Handle long texts with chunking
+        chunk_size = 500  # characters
+        chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
+        full_summary = ""
+        for chunk in chunks:
+            summ = models[selected_model](chunk, max_length=max_length, min_length=min_length, do_sample=False)[0]['summary_text']
+            full_summary += summ + " "
+
+        st.subheader(f"Summary ({selected_model}):")
+        st.write(full_summary)
+
+        # Translation
+        if target_lang != "None":
+            lang_code = target_lang[:2].lower()
+            try:
+                translation = translator.translate(full_summary, dest=lang_code).text
+                st.subheader(f"Summary in {target_lang}:")
+                st.write(translation)
+            except Exception as e:
+                st.warning(f"Translation failed: {str(e)}")
+
+        # Model comparison
+        if show_comparison:
+            st.subheader("Comparison with other models:")
+            for model_name, model_pipeline in models.items():
+                if model_name != selected_model:
+                    comp_summary = ""
+                    for chunk in chunks:
+                        comp_summary += model_pipeline(chunk, max_length=max_length, min_length=min_length, do_sample=False)[0]['summary_text'] + " "
+                    st.markdown(f"**{model_name} Summary:** {comp_summary}")
+
+        # ROUGE Evaluation
+        if show_rouge and reference_text.strip():
+            scores = scorer.score(reference_text, full_summary)
+            st.subheader("ROUGE Scores:")
+            for k, v in scores.items():
+                st.write(f"{k}: Precision: {v.precision:.3f}, Recall: {v.recall:.3f}, F1: {v.fmeasure:.3f}")