Spaces:
Sleeping
Sleeping
File size: 4,495 Bytes
d90e4dc 84669bc d90e4dc 23b0057 12244e9 d90e4dc 12244e9 d90e4dc |
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 |
import os
import gradio as gr
from transformers import pipeline
import spacy
import subprocess
import nltk
from nltk.corpus import wordnet
import torch
from gramformer import Gramformer
# Initialize the English text classification pipeline for AI detection
pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
# Initialize Gramformer
gf = Gramformer(models=1, use_gpu=False) # 1 = corrector
# 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 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 -> Grammar Correction (Humanifier)
def paraphrase_correct_and_grammar(text):
# Step 1: Paraphrase the text
paraphrased_text = paraphrase_with_spacy_nltk(text)
# Step 2: Capitalize sentences and proper nouns
capitalized_text = capitalize_sentences_and_nouns(paraphrased_text)
# Step 3: Grammar correction using Gramformer
corrected_sentences = gf.correct(capitalized_text, max_candidates=1)
final_text = next(iter(corrected_sentences)) if corrected_sentences else capitalized_text
return final_text
# Gradio app setup with two tabs
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')
# 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 & Grammar Check")
output_text = gr.Textbox(label="Processed Text")
# Connect the paraphrasing and grammar correction function to the button
paraphrase_button.click(paraphrase_correct_and_grammar, inputs=text_input, outputs=output_text)
# Launch the app with both functionalities
demo.launch() |