Update app.py

app.py

@@ -1,11 +1,12 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 import torch
 import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
 from gensim import downloader as api
+from gingerit.gingerit import GingerIt  # Import GingerIt for grammar correction
 
 # Ensure necessary NLTK data is downloaded
 nltk.download('wordnet')
@@ -28,9 +29,6 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
 model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english").to(device)
 
-# Load grammar correction model from Hugging Face
-grammar_corrector = pipeline("text2text-generation", model="pszemraj/flan-t5-large-grammar-synthesis", device=0 if torch.cuda.is_available() else -1)
-
 # AI detection function using DistilBERT
 def detect_ai_generated(text):
     inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512).to(device)
@@ -48,7 +46,7 @@ def get_synonyms_nltk(word, pos):
         return [lemma.name() for lemma in lemmas]
     return []
 
-# Paraphrasing function using spaCy and NLTK
+# Paraphrasing function using spaCy and NLTK (without grammar correction)
 def paraphrase_with_spacy_nltk(text):
     doc = nlp(text)
     paraphrased_words = []
@@ -78,10 +76,11 @@ def paraphrase_with_spacy_nltk(text):
     
     return paraphrased_sentence
 
-# Grammar correction function using FLAN-T5
+# Grammar correction function using GingerIt
 def correct_grammar(text):
-    corrected_text = grammar_corrector(text)[0]['generated_text']
-    return corrected_text
+    parser = GingerIt()
+    result = parser.parse(text)
+    return result['result']  # Return the corrected text
 
 # Combined function: Paraphrase -> Grammar Check
 def paraphrase_and_correct(text):