Spaces:
Running
Running
| import easyocr | |
| from gradio_client import Client, handle_file | |
| import pandas as pd | |
| import gradio as gr | |
| clientImg = Client("dj-dawgs-ipd/IPD-Image-ViT-Finetune") | |
| clientEngText = Client("dj-dawgs-ipd/IPD-Text-English-Finetune") | |
| clientHingText = Client("dj-dawgs-ipd/IPD-Text-Hinglish") | |
| profanity_df = pd.read_csv('Hinglish_Profanity_List.csv' , encoding = 'utf-8') | |
| profanity_hn = profanity_df['profanity_hn'] | |
| def extract_text(image): | |
| reader = easyocr.Reader(['en']) | |
| data = [result[1] for result in reader.readtext(image)] | |
| return ' '.join([l for l in data]) | |
| def predict(image): | |
| imgResult = clientImg.predict( | |
| image=handle_file(image), | |
| api_name="/predict" | |
| ) | |
| label , confidence = imgResult[0]['label'] , float(imgResult[1]['label']) | |
| if (label == 'finger_gun_to_the_head' and confidence > 0.98) or (label != 'finger_gun_to_the_head' and confidence > 0.95): | |
| return { | |
| "prediction" : "hate", | |
| "language" : None, | |
| "label" : label, | |
| "confidence" : confidence, | |
| "hate_text" : None | |
| } | |
| else: | |
| ocr_text = extract_text(image).lower() | |
| engResult = clientEngText.predict( | |
| text=ocr_text[:200], | |
| api_name="/predict" | |
| ) | |
| hingResult = clientHingText.predict( | |
| text=ocr_text[:200], | |
| api_name="/predict" | |
| ) | |
| profanityFound = [word for word in ocr_text.split() if word in profanity_hn] | |
| if len(profanityFound) > 0: | |
| return { | |
| "prediction" : "hate", | |
| "language" : "Hindi", | |
| "label" : "Profanity Found", | |
| "confidence" : None, | |
| "hate_text" : profanityFound | |
| } | |
| elif engResult[0] != "NEITHER" and engResult[1] > 0.5: | |
| return { | |
| "prediction" : "hate", | |
| "language" : "English", | |
| "label" : engResult[0], | |
| "confidence" : engResult[1], | |
| "hate_text" : ocr_text[:200] | |
| } | |
| elif hingResult[0] != "NAG" and hingResult[1] > 0.5: | |
| return { | |
| "prediction" : "hate", | |
| "language" : "Hinglish", | |
| "label" : hingResult[0], | |
| "confidence" : hingResult[1], | |
| "hate_text" : ocr_text[:200] | |
| } | |
| else: | |
| return { | |
| "prediction" : "not_hate", | |
| "language" : None, | |
| "label" : "No hate found, yay!", | |
| "confidence" : None, | |
| "hate_text" : None | |
| } | |
| iface = gr.Interface(fn=predict, | |
| inputs = gr.Image(type='filepath'), | |
| outputs=gr.JSON(), | |
| title = "Hate Speech Detection in Image", | |
| description = "Detect hateful symbols or text in Image" | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() |