Rename project to "Smooth Paraphraser"

- Updated all references of the app name from "Paraphrasing App" to "Smooth Paraphraser".
- Adjusted UI titles, headers, and documentation accordingly.
- Ensures consistent branding across the application.

README.md

@@ -1,39 +1,14 @@
----
-title: Paraphrasing App
-emoji: 🔄
-colorFrom: indigo
-colorTo: blue
-sdk: gradio
-sdk_version: "4.29.0"
-app_file: app.py
-pinned: false
----
+# Smooth Paraphraser
 
-# 🔄 Paraphrasing App
+Smooth Paraphraser is a simple Hugging Face Space app built with **Gradio** and a pretrained **T5 model** for paraphrasing text.
 
-This Space uses a **T5 transformer model** to paraphrase input text into different variations.  
-It is built with **Gradio** and **Hugging Face Transformers**.
+## Features
+- Enter any text and get a smooth paraphrased version.
+- Powered by Hugging Face `transformers` library.
+- Runs with Gradio for a clean UI.
 
-## 🚀 Features
-- Enter any sentence or paragraph
-- Get multiple paraphrased outputs
-- Powered by pretrained **T5 model**
-
-## 🛠️ Requirements
-All dependencies are listed in `requirements.txt`:
-- `transformers`
-- `torch`
-- `sentencepiece`
-- `tiktoken`
-- `gradio`
-
-## 💡 Example
-Input:  
-> "The quick brown fox jumps over the lazy dog."
-
-Output:  
-- "A fast brown fox leaps over a lazy dog."  
-- "The lazy dog was jumped over by a quick brown fox."  
-
----
-Built with ❤️ using Hugging Face Spaces
+## How to Run Locally
+```bash
+pip install -r requirements.txt
+python app.py
+```

app.py

@@ -1,29 +1,20 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import pipeline
 
-# Load model and tokenizer
-model_name = "t5-small"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+# Load paraphrasing pipeline
+paraphraser = pipeline("text2text-generation", model="Vamsi/T5_Paraphrase_Paws")
 
-def paraphrase(text, num_return_sequences=3, num_beams=5):
-    input_text = "paraphrase: " + text + " </s>"
-    inputs = tokenizer.encode(input_text, return_tensors="pt", max_length=512, truncation=True)
-    outputs = model.generate(
-        inputs,
-        max_length=512,
-        num_beams=num_beams,
-        num_return_sequences=num_return_sequences,
-        temperature=1.5
-    )
-    return [tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True) for output in outputs]
+def paraphrase(text):
+    result = paraphraser(text, max_length=100, num_return_sequences=1)
+    return result[0]['generated_text']
 
+# Gradio interface
 demo = gr.Interface(
     fn=paraphrase,
-    inputs=[gr.Textbox(lines=3, label="Enter text"), gr.Slider(1, 5, value=3, step=1, label="Number of outputs")],
-    outputs=gr.List(label="Paraphrased Sentences"),
-    title="🔄 Paraphrasing App",
-    description="Paraphrase any input text using a pretrained T5 transformer model."
+    inputs=gr.Textbox(lines=4, placeholder="Enter text to paraphrase..."),
+    outputs="text",
+    title="Smooth Paraphraser",
+    description="A simple app to smoothly paraphrase text using a pretrained T5 transformer model."
 )
 
 if __name__ == "__main__":

requirements.txt

@@ -1,5 +1,3 @@
-transformers
+transformers==4.42.4
 torch
-sentencepiece
-tiktoken
 gradio==4.29.0