File size: 5,294 Bytes
b0503ee
84669bc
7feda08
51568dc
7fc55d1
 
9079e3b
51568dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7fc55d1
51568dc
6ba2176
51568dc
6ba2176
 
 
c163eb2
6ba2176
7feda08
51568dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c163eb2
51568dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c163eb2
51568dc
 
 
 
 
c163eb2
51568dc
96ac1ff
51568dc
 
 
 
 
 
 
c163eb2
51568dc
 
 
 
 
 
 
 
 
 
 
c163eb2
51568dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96ac1ff
 
 
 
 
51568dc
 
aed9390
51568dc
c163eb2
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
import os
import gradio as gr
import spacy
import subprocess
import nltk
from nltk.corpus import wordnet

# Clone and install CorrectLy
def install_correctly():
    if not os.path.exists('CorrectLy'):
        print("Cloning CorrectLy repository...")
        subprocess.run(["git", "clone", "https://github.com/rounakdatta/CorrectLy.git"], check=True)
        
        # Install dependencies from CorrectLy
        subprocess.run([sys.executable, "-m", "pip", "install", "-r", "CorrectLy/requirements.txt"], check=True)

        # Add CorrectLy to Python path
        sys.path.append(os.path.abspath('CorrectLy'))

# Install CorrectLy
install_correctly()

# Import CorrectLy after installation
from CorrectLy.correctly import CorrectLy

# Initialize CorrectLy for grammar correction
corrector = CorrectLy()

# Initialize the English text classification pipeline for AI detection
from transformers import pipeline
pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")

# Function to predict the label and score for English text (AI Detection)
def predict_en(text):
    res = pipeline_en(text)[0]
    return res['label'], res['score']

# Ensure necessary NLTK data is downloaded for Humanifier
nltk.download('wordnet')
nltk.download('omw-1.4')

# Ensure the SpaCy model is installed for Humanifier
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")

# Function to correct grammar using CorrectLy
def correct_grammar_with_correctly(text):
    return corrector.correct(text)

# 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"):
        t1 = gr.Textbox(lines=5, label='Text')
        button1 = gr.Button("๐Ÿค– Predict!")
        label1 = gr.Textbox(lines=1, label='Predicted Label ๐ŸŽƒ')
        score1 = gr.Textbox(lines=1, label='Prob')

        # Connect the prediction function to the button
        button1.click(predict_en, inputs=[t1], outputs=[label1, score1], api_name='predict_en')
    
    with gr.Tab("Humanifier"):
        text_input = gr.Textbox(lines=5, label="Input Text")
        paraphrase_button = gr.Button("Paraphrase & Correct")
        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)
    
    with gr.Tab("Grammar Correction"):
        grammar_input = gr.Textbox(lines=5, label="Input Text")
        grammar_button = gr.Button("Correct Grammar")
        grammar_output = gr.Textbox(label="Corrected Text")

        # Connect the CorrectLy grammar correction function to the button
        grammar_button.click(correct_grammar_with_correctly, inputs=grammar_input, outputs=grammar_output)

# Launch the app with all functionalities
demo.launch()