Add text summarizer CPU Space

README.md

@@ -1,12 +1,13 @@
 ---
-title: Text Summarizer Cpu
-emoji: 📊
-colorFrom: pink
-colorTo: blue
+title: Text Summarizer CPU
+colorFrom: blue
+colorTo: green
 sdk: gradio
-sdk_version: 6.10.0
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Text Summarizer CPU
+
+Free CPU text summarizer using `google/flan-t5-small`.

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+
+from summary_tool.service import SummaryService
+
+
+service = SummaryService()
+
+
+def summarize_text(text, style, max_words):
+    return service.summarize(text, style, int(max_words))
+
+
+with gr.Blocks(
+    title="Text Summarizer CPU",
+    theme=gr.themes.Soft(primary_hue="blue", secondary_hue="green"),
+) as demo:
+    gr.Markdown(
+        """
+        # Text Summarizer CPU
+        Paste long text and generate a short AI summary on free CPU.
+        """
+    )
+
+    text_input = gr.Textbox(label="Input Text", lines=12, placeholder="Paste article, notes, or long text here")
+    style_input = gr.Dropdown(
+        choices=["Short", "Balanced", "Detailed", "Bullet Points"],
+        value="Balanced",
+        label="Summary Style",
+    )
+    max_words_input = gr.Slider(40, 240, value=120, step=10, label="Max Words")
+    run_button = gr.Button("Summarize", variant="primary")
+
+    summary_output = gr.Textbox(label="Summary", lines=8)
+    status_output = gr.Textbox(label="Status", lines=2)
+
+    run_button.click(
+        fn=summarize_text,
+        inputs=[text_input, style_input, max_words_input],
+        outputs=[summary_output, status_output],
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio>=5.23.0
+huggingface_hub>=0.34.0,<1.0
+safetensors>=0.5.3
+torch>=2.3.0
+transformers>=4.49.0

summary_tool/__init__.py

@@ -0,0 +1,3 @@
+from .service import SummaryService
+
+__all__ = ["SummaryService"]

summary_tool/service.py

@@ -0,0 +1,65 @@
+import os
+
+import torch
+
+
+MODEL_ID = "google/flan-t5-small"
+
+
+class SummaryService:
+    def __init__(self):
+        self.pipe = None
+        cpu_count = os.cpu_count() or 1
+        torch.set_num_threads(max(1, min(4, cpu_count)))
+
+    def summarize(self, text, style, max_words):
+        clean_text = " ".join((text or "").split())
+        if not clean_text:
+            return "", "Paste text first."
+
+        try:
+            prompt = self._build_prompt(clean_text, style, max_words)
+            summary = self._run_model(prompt)
+            if style == "Bullet Points":
+                summary = self._normalize_bullets(summary)
+            return summary, f"Generated summary with {MODEL_ID}."
+        except Exception as exc:
+            return "", f"Summarization failed: {type(exc).__name__}: {exc}"
+
+    def _load_pipeline(self):
+        if self.pipe is not None:
+            return
+
+        from transformers import pipeline
+
+        self.pipe = pipeline(
+            "text2text-generation",
+            model=MODEL_ID,
+            device=-1,
+        )
+
+    def _run_model(self, prompt):
+        self._load_pipeline()
+        result = self.pipe(
+            prompt,
+            max_new_tokens=220,
+            do_sample=False,
+        )
+        return (result[0].get("generated_text") or "").strip()
+
+    def _build_prompt(self, text, style, max_words):
+        if style == "Short":
+            instruction = f"Summarize this text in under {max_words} words using plain language."
+        elif style == "Detailed":
+            instruction = f"Write a detailed summary in under {max_words} words."
+        elif style == "Bullet Points":
+            instruction = f"Summarize this text as concise bullet points in under {max_words} words."
+        else:
+            instruction = f"Write a balanced summary in under {max_words} words."
+        return f"{instruction}\n\nText:\n{text}"
+
+    def _normalize_bullets(self, text):
+        lines = [line.strip(" -") for line in text.splitlines() if line.strip()]
+        if not lines:
+            return text
+        return "\n".join(f"- {line}" for line in lines[:8])