Update app.py

app.py

@@ -1,11 +1,13 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
 from gensim import downloader as api
+from autocorrect import Speller  # Autocorrect library for spelling correction
+from gingerit.gingerit import GingerIt  # GingerIt for grammar correction
 
 # Ensure necessary NLTK data is downloaded
 nltk.download('wordnet')
@@ -28,9 +30,11 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 tokenizer_ai = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
 model_ai = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english").to(device)
 
-# Load grammar correction model and tokenizer from Hugging Face
-tokenizer_gc = AutoTokenizer.from_pretrained("prithivida/grammar_error_correcter_v1")
-model_gc = AutoModelForSeq2SeqLM.from_pretrained("prithivida/grammar_error_correcter_v1").to(device)
+# Initialize Autocorrect for spelling correction
+spell = Speller()
+
+# Initialize GingerIt for grammar correction
+parser = GingerIt()
 
 # AI detection function using DistilBERT
 def detect_ai_generated(text):
@@ -123,14 +127,17 @@ def paraphrase_with_spacy_nltk(text):
     
     return corrected_text
 
-# Function to correct grammar using Hugging Face model
-def correct_grammar(text):
-    inputs = tokenizer_gc.encode("gec: " + text, return_tensors="pt", truncation=True).to(device)
-    outputs = model_gc.generate(inputs, max_length=512, num_beams=5, early_stopping=True)
-    corrected_text = tokenizer_gc.decode(outputs[0], skip_special_tokens=True)
-    return corrected_text
+# Function to correct spelling using autocorrect and grammar using GingerIt
+def correct_spelling_and_grammar(text):
+    # Step 1: Correct spelling using autocorrect
+    corrected_spelling = spell(text)
+    
+    # Step 2: Correct grammar using GingerIt
+    grammar_correction = parser.parse(corrected_spelling)
+    
+    return grammar_correction['result']
 
-# Combined function: Paraphrase -> Tense Check -> Capitalization -> Grammar Correction
+# Combined function: Paraphrase -> Tense Check -> Capitalization -> Spelling and Grammar Correction
 def paraphrase_and_correct(text):
     # Step 1: Paraphrase the text
     paraphrased_text = paraphrase_with_spacy_nltk(text)
@@ -141,8 +148,8 @@ def paraphrase_and_correct(text):
     # Step 3: Capitalize sentences and proper nouns
     capitalized_text = capitalize_sentences_and_nouns(tense_checked_text)
     
-    # Step 4: Correct grammar using Hugging Face model
-    final_text = correct_grammar(capitalized_text)
+    # Step 4: Correct spelling and grammar
+    final_text = correct_spelling_and_grammar(capitalized_text)
     
     return final_text