Update app.py

app.py

@@ -1,12 +1,38 @@
 import os
+import subprocess
+import sys
 import gradio as gr
 from transformers import pipeline
 import spacy
-import subprocess
 import nltk
 from nltk.corpus import wordnet
+
+# Function to install GECToR
+def install_gector():
+    if not os.path.exists('gector'):
+        print("Cloning GECToR repository...")
+        subprocess.run(["git", "clone", "https://github.com/grammarly/gector.git"], check=True)
+        
+        # Install dependencies from GECToR requirements
+        subprocess.run([sys.executable, "-m", "pip", "install", "-r", "gector/requirements.txt"], check=True)
+
+        # Manually add GECToR to the Python path
+        sys.path.append(os.path.abspath('gector'))
+
+# Install and import GECToR
+install_gector()
+
+# Ensure the gector module path is added correctly
+sys.path.insert(0, os.path.abspath('./gector'))
+
+# Import GECToR after installation
 from gector.gec_model import GecBERTModel
 
+# Initialize GECToR model for grammar correction
+gector_model = GecBERTModel(vocab_path='gector/data/output_vocabulary',
+                            model_paths=['https://grammarly-nlp-data.s3.amazonaws.com/gector/roberta_1_gector.th'],
+                            is_ensemble=False)
+
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
 
@@ -23,92 +49,18 @@ nltk.download('omw-1.4')
 try:
     nlp = spacy.load("en_core_web_sm")
 except OSError:
-    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
+    subprocess.run([sys.executable, "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Initialize GECToR model for grammar correction
-gector_model = GecBERTModel(vocab_path='data/output_vocabulary',
-                            model_paths=['https://grammarly-nlp-data.s3.amazonaws.com/gector/roberta_1_gector.th'],
-                            is_ensemble=False)
-
 # Function to correct grammar using GECToR
 def correct_grammar_with_gector(text):
     corrected_sentences = []
-    sentences = [text]  # If you want to split into sentences, you can implement that here
+    sentences = [text]
     for sentence in sentences:
         preds = gector_model.handle_batch([sentence])
         corrected_sentences.append(preds[0])
     return ' '.join(corrected_sentences)
 
-# Function to get synonyms using NLTK WordNet (Humanifier)
-def get_synonyms_nltk(word, pos):
-    synsets = wordnet.synsets(word, pos=pos)
-    if synsets:
-        lemmas = synsets[0].lemmas()
-        return [lemma.name() for lemma in lemmas]
-    return []
-
-# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
-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:  # First word of the sentence
-                sentence.append(token.text.capitalize())
-            elif token.pos_ == "PROPN":  # Proper noun
-                sentence.append(token.text.capitalize())
-            else:
-                sentence.append(token.text)
-        corrected_text.append(' '.join(sentence))
-
-    return ' '.join(corrected_text)
-
-# Paraphrasing function using SpaCy and NLTK (Humanifier)
-def paraphrase_with_spacy_nltk(text):
-    doc = nlp(text)
-    paraphrased_words = []
-    
-    for token in doc:
-        # Map SpaCy POS tags to WordNet POS tags
-        pos = None
-        if token.pos_ in {"NOUN"}:
-            pos = wordnet.NOUN
-        elif token.pos_ in {"VERB"}:
-            pos = wordnet.VERB
-        elif token.pos_ in {"ADJ"}:
-            pos = wordnet.ADJ
-        elif token.pos_ in {"ADV"}:
-            pos = wordnet.ADV
-        
-        synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else []
-        
-        # Replace with a synonym only if it makes sense
-        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower():
-            paraphrased_words.append(synonyms[0])
-        else:
-            paraphrased_words.append(token.text)
-    
-    # Join the words back into a sentence
-    paraphrased_sentence = ' '.join(paraphrased_words)
-    
-    # Capitalize sentences and proper nouns
-    corrected_text = capitalize_sentences_and_nouns(paraphrased_sentence)
-    
-    return corrected_text
-
-# Combined function: Paraphrase -> Capitalization (Humanifier)
-def paraphrase_and_correct(text):
-    # Step 1: Paraphrase the text
-    paraphrased_text = paraphrase_with_spacy_nltk(text)
-    
-    # Step 2: Capitalize sentences and proper nouns
-    final_text = capitalize_sentences_and_nouns(paraphrased_text)
-    
-    return final_text
-
 # Gradio app setup with three tabs
 with gr.Blocks() as demo:
     with gr.Tab("AI Detection"):
@@ -126,7 +78,7 @@ with gr.Blocks() as demo:
         output_text = gr.Textbox(label="Paraphrased Text")
 
         # Connect the paraphrasing function to the button
-        paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
+        paraphrase_button.click(correct_grammar_with_gector, inputs=text_input, outputs=output_text)
     
     with gr.Tab("Grammar Correction"):
         grammar_input = gr.Textbox(lines=5, label="Input Text")