Update app.py

app.py

@@ -1,6 +1,4 @@
 import gradio as gr
-from docx import Document
-import io
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import re
 
@@ -8,20 +6,7 @@ import re
 tokenizer = AutoTokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")
 model = AutoModelForSeq2SeqLM.from_pretrained("Vamsi/T5_Paraphrase_Paws")
 
-def fix_punctuation(text):
-    """
-    Fix spacing around commas, periods, semicolons, colons, exclamation and question marks.
-    Removes space before punctuation and ensures exactly one space after punctuation.
-    """
-    # Remove space before punctuation
-    text = re.sub(r'\s+([,.!?;:])', r'\1', text)
-    # Ensure single space after punctuation if not end of line
-    text = re.sub(r'([,.!?;:])([^\s\n])', r'\1 \2', text)
-    # Normalize multiple spaces
-    text = re.sub(r'\s+', ' ', text)
-    # Remove spaces at start/end
-    return text.strip()
-
+# Function to paraphrase a single chunk
 def paraphrase_text(text):
     input_text = f"paraphrase: {text} </s>"
     input_ids = tokenizer.encode(input_text, return_tensors="pt", truncation=True)
@@ -31,43 +16,33 @@ def paraphrase_text(text):
         do_sample=True,
         top_k=120,
         top_p=0.95,
-        temperature=1.5
+        temperature=1.3
     )
-    paraphrased = tokenizer.decode(output_ids[0], skip_special_tokens=True)
-    return fix_punctuation(paraphrased)
+    return tokenizer.decode(output_ids[0], skip_special_tokens=True)
 
+# Split text into chunks (4 sentences each)
 def chunk_text(text, max_sentences=4):
     sentences = re.split(r'(?<=[.!?]) +', text.strip())
     return [' '.join(sentences[i:i+max_sentences]) for i in range(0, len(sentences), max_sentences)]
 
+# Paraphrase the full text
 def full_article_paraphrase(text):
     chunks = chunk_text(text)
     return "\n\n".join(paraphrase_text(chunk.strip()) for chunk in chunks if chunk.strip())
 
-def extract_text_from_docx(file_obj):
-    file_bytes = file_obj.read() if hasattr(file_obj, "read") else file_obj
-    doc = Document(io.BytesIO(file_bytes))
-    return "\n".join([para.text for para in doc.paragraphs if para.text.strip()])
-
-def full_pipeline(input_text=None, file=None):
-    if file is not None:
-        input_text = extract_text_from_docx(file)
+# Gradio pipeline
+def paraphrase_pipeline(input_text):
     if not input_text or len(input_text.strip()) < 10:
-        return "Please enter or upload valid text."
-    result = full_article_paraphrase(input_text)
-    return result
+        return "Please enter valid text."
+    return full_article_paraphrase(input_text)
 
+# Gradio interface
 demo = gr.Interface(
-    fn=full_pipeline,
-    inputs=[
-        gr.Textbox(label="Paste Text (optional)", lines=20, placeholder="Or upload a .docx file below..."),
-        gr.File(label="Upload .docx File (optional)", file_types=[".docx"])
-    ],
-    outputs=[
-        gr.Textbox(label="Paraphrased Output")
-    ],
+    fn=paraphrase_pipeline,
+    inputs=gr.Textbox(label="Paste Text Here", lines=20, placeholder="Enter your text..."),
+    outputs=gr.Textbox(label="Paraphrased Text"),
     title="Smart Paraphraser",
-    description="Paste or upload your article. Get paraphrased output."
+    description="Paste your text and get paraphrased output instantly."
 )
 
 if __name__ == "__main__":