Update app.py

app.py

@@ -81,128 +81,6 @@ def plagiarism_removal(text):
 
     return " ".join(corrected_text)
 
-def predict_en(text):
-    res = pipeline_en(text)[0]
-    return res['label'], res['score']
-
-def remove_redundant_words(text):
-    doc = nlp(text)
-    meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
-    filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
-    return ' '.join(filtered_text)
-
-def fix_punctuation_spacing(text):
-    words = text.split(' ')
-    cleaned_words = []
-    punctuation_marks = {',', '.', "'", '!', '?', ':'}
-
-    for word in words:
-        if cleaned_words and word and word[0] in punctuation_marks:
-            cleaned_words[-1] += word
-        else:
-            cleaned_words.append(word)
-
-    return ' '.join(cleaned_words).replace(' ,', ',').replace(' .', '.').replace(" '", "'") \
-                                    .replace(' !', '!').replace(' ?', '?').replace(' :', ':')
-
-def fix_possessives(text):
-    text = re.sub(r'(\w)\s\'\s?s', r"\1's", text)
-    return text
-
-def capitalize_sentences_and_nouns(text):
-    doc = nlp(text)
-    corrected_text = []
-
-    for sent in doc.sents:
-        sentence = []
-        for token in sent:
-            if token.i == sent.start:
-                sentence.append(token.text.capitalize())
-            elif token.pos_ == "PROPN":
-                sentence.append(token.text.capitalize())
-            else:
-                sentence.append(token.text)
-        corrected_text.append(' '.join(sentence))
-
-    return ' '.join(corrected_text)
-
-def force_first_letter_capital(text):
-    sentences = re.split(r'(?<=\w[.!?])\s+', text)
-    capitalized_sentences = []
-    
-    for sentence in sentences:
-        if sentence:
-            capitalized_sentence = sentence[0].capitalize() + sentence[1:]
-            if not re.search(r'[.!?]$', capitalized_sentence):
-                capitalized_sentence += '.'
-            capitalized_sentences.append(capitalized_sentence)
-    
-    return " ".join(capitalized_sentences)
-
-def correct_tense_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
-            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
-            corrected_text.append(lemma)
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-def correct_article_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.text in ['a', 'an']:
-            next_token = token.nbor(1)
-            if token.text == "a" and next_token.text[0].lower() in "aeiou":
-                corrected_text.append("an")
-            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
-                corrected_text.append("a")
-            else:
-                corrected_text.append(token.text)
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-def ensure_subject_verb_agreement(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.dep_ == "nsubj" and token.head.pos_ == "VERB":
-            if token.tag_ == "NN" and token.head.tag_ != "VBZ":
-                corrected_text.append(token.head.lemma_ + "s")
-            elif token.tag_ == "NNS" and token.head.tag_ == "VBZ":
-                corrected_text.append(token.head.lemma_)
-        corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-def correct_spelling(text):
-    words = text.split()
-    corrected_words = []
-    for word in words:
-        corrected_word = spell.correction(word)
-        if corrected_word is not None:
-            corrected_words.append(corrected_word)
-        else:
-            corrected_words.append(word)
-    return ' '.join(corrected_words)
-
-
-
-
-def correct_grammar_with_gpt(text):
-    # Initialize a pipeline for text generation with a suitable model for grammar correction
-    gpt_model = pipeline("text-generation", model="gpt2")  # Replace with a grammar correction model if available
-    
-    # Generate a corrected version of the text
-    corrected_output = gpt_model(text, max_length=50)[0]['generated_text']
-    
-    return corrected_output.strip()
-
-
-
 def paraphrase_and_correct(text):
     paragraphs = text.split("\n\n")  # Split by paragraphs
 
@@ -219,11 +97,10 @@ def paraphrase_and_correct(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)
 
-    # Use GPT for final grammar correction
-        final_corrected_text = correct_grammar_with_gpt(paraphrased_text)
+    return "\n\n".join(processed_paragraphs)  # Reassemble the text with paragraphs
 
-        return final_corrected_text
 # Gradio app setup
 with gr.Blocks() as demo:
     with gr.Tab("AI Detection"):