Update app.py

app.py

@@ -1,121 +1,33 @@
-import os
 import gradio as gr
-from transformers import pipeline
-import spacy
-import subprocess
-import nltk
-from nltk.corpus import wordnet
-from nltk.corpus import stopwords
-from nltk.tokenize import word_tokenize
-from spellchecker import SpellChecker
-import re
-import string
-import random
-
-# Download necessary NLTK data
-nltk.download('punkt')
-nltk.download('stopwords')
-nltk.download('averaged_perceptron_tagger')
-nltk.download('averaged_perceptron_tagger_eng')
-nltk.download('wordnet')
-nltk.download('omw-1.4')
-nltk.download('punkt_tab')
-
-# Initialize stopwords
-stop_words = set(stopwords.words("english"))
-
-# Words we don't want to replace
-exclude_tags = {'PRP', 'PRP$', 'MD', 'VBZ', 'VBP', 'VBD', 'VBG', 'VBN', 'TO', 'IN', 'DT', 'CC'}
-exclude_words = {'is', 'am', 'are', 'was', 'were', 'have', 'has', 'do', 'does', 'did', 'will', 'shall', 'should', 'would', 'could', 'can', 'may', 'might'}
-
-# Initialize the English text classification pipeline for AI detection
-pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
-
-# Initialize the spell checker
-spell = SpellChecker()
-
-# Ensure the SpaCy model is installed
-try:
-    nlp = spacy.load("en_core_web_sm")
-except OSError:
-    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
-    nlp = spacy.load("en_core_web_sm")
-
-def plagiarism_removal(text):
-    def plagiarism_remover(word):
-        if word.lower() in stop_words or word.lower() in exclude_words or word in string.punctuation:
-            return word
-        
-        # Find synonyms
-        synonyms = set()
-        for syn in wordnet.synsets(word):
-            for lemma in syn.lemmas():
-                if "_" not in lemma.name() and lemma.name().isalpha() and lemma.name().lower() != word.lower():
-                    synonyms.add(lemma.name())
-
-        pos_tag_word = nltk.pos_tag([word])[0]
-
-        if pos_tag_word[1] in exclude_tags:
-            return word
-        
-        filtered_synonyms = [syn for syn in synonyms if nltk.pos_tag([syn])[0][1] == pos_tag_word[1]]
-
-        if not filtered_synonyms:
-            return word
-
-        synonym_choice = random.choice(filtered_synonyms)
-
-        if word.istitle():
-            return synonym_choice.title()
-        return synonym_choice
-
-    para_split = word_tokenize(text)
-    final_text = [plagiarism_remover(word) for word in para_split]
+import torch
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# Load the grammar correction model
+model_name = "microsoft/deberta-v3-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+# Function to correct grammar
+def correct_grammar(text):
+    # Encode input text
+    inputs = tokenizer.encode(text, return_tensors="pt")
     
-    corrected_text = []
-    for i in range(len(final_text)):
-        if final_text[i] in string.punctuation and i > 0:
-            corrected_text[-1] += final_text[i]  
-        else:
-            corrected_text.append(final_text[i])
-
-    return " ".join(corrected_text)
-
-def paraphrase_and_correct(text):
-    paragraphs = text.split("\n\n")  # Split by paragraphs
-
-    # Process each paragraph separately
-    processed_paragraphs = []
-    for paragraph in paragraphs:
-        cleaned_text = remove_redundant_words(paragraph)
-        plag_removed = plagiarism_removal(cleaned_text)
-        paraphrased_text = capitalize_sentences_and_nouns(plag_removed)
-        paraphrased_text = force_first_letter_capital(paraphrased_text)
-        paraphrased_text = correct_article_errors(paraphrased_text)
-        paraphrased_text = correct_tense_errors(paraphrased_text)
-        paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
-        paraphrased_text = fix_possessives(paraphrased_text)
-        paraphrased_text = correct_spelling(paraphrased_text)
-        paraphrased_text = fix_punctuation_spacing(paraphrased_text)
-        processed_paragraphs.append(paraphrased_text)
-
-    return "\n\n".join(processed_paragraphs)  # Reassemble the text with paragraphs
-
-# Gradio app setup
-with gr.Blocks() as demo:
-    with gr.Tab("AI Detection"):
-        t1 = gr.Textbox(lines=5, label='Text')
-        button1 = gr.Button("🤖 Predict!")
-        label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
-        score1 = gr.Textbox(lines=1, label='Prob')
-
-        button1.click(fn=predict_en, inputs=t1, outputs=[label1, score1])
-
-    with gr.Tab("Paraphrasing & Grammar Correction"):
-        t2 = gr.Textbox(lines=5, label='Enter text for paraphrasing and grammar correction')
-        button2 = gr.Button("🔄 Paraphrase and Correct")
-        result2 = gr.Textbox(lines=5, label='Corrected Text')
-
-        button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
-
-demo.launch(share=True)
+    # Generate the corrected text
+    with torch.no_grad():
+        outputs = model.generate(inputs, max_length=512, num_beams=5, early_stopping=True)
+
+    # Decode the corrected text
+    corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return corrected_text
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=correct_grammar,
+    inputs="text",
+    outputs="text",
+    title="Grammar Correction",
+    description="Enter a sentence or paragraph to receive grammar corrections using DeBERTa."
+)
+
+if __name__ == "__main__":
+    interface.launch()