Update app.py

app.py

@@ -1,30 +1,40 @@
+# app.py
+
 import gradio as gr
-from transformers import T5Tokenizer, T5ForConditionalGeneration
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-# Load pretrained T5 model for paraphrasing
 model_name = "Vamsi/T5_Paraphrase_Paws"
-tokenizer = T5Tokenizer.from_pretrained(model_name)
-model = T5ForConditionalGeneration.from_pretrained(model_name)
-
-def paraphrase_text(input_text):
-    # Prepare input text
-    input_ids = tokenizer.encode("paraphrase: " + input_text + " </s>", return_tensors="pt", max_length=512, truncation=True)
-    
-    # Generate paraphrase
-    outputs = model.generate(input_ids, max_length=256, num_return_sequences=1, temperature=1.5)
-    
-    # Decode output
-    paraphrased_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return paraphrased_text
-
-# Create Gradio interface
-demo = gr.Interface(
-    fn=paraphrase_text,
-    inputs=gr.Textbox(lines=5, placeholder="Enter text to paraphrase..."),
-    outputs="text",
-    title="AI Paraphraser",
-    description="Paste any English text to get a paraphrased version using T5 model."
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+def paraphrase(text):
+    if not text.strip():
+        return "No input provided."
+
+    input_ids = tokenizer(
+        "paraphrase: " + text,
+        return_tensors="pt",
+        padding="longest",
+        truncation=True,
+        max_length=256,
+    ).input_ids
+
+    outputs = model.generate(
+        input_ids,
+        max_length=256,
+        num_return_sequences=1,
+        num_beams=5,
+        temperature=1.5,
+    )
+
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+iface = gr.Interface(
+    fn=paraphrase,
+    inputs=gr.Textbox(lines=4, label="Enter Text to Paraphrase"),
+    outputs=gr.Textbox(label="Paraphrased Text"),
+    title="Paraphraser Tool",
+    allow_flagging="never",
 )
 
-# Expose /run/predict endpoint
-demo.launch()
+iface.launch()