import datetime import gradio as gr from huggingface_hub import hf_hub_download from langdetect import detect, DetectorFactory, detect_langs import fasttext from transformers import pipeline models = {'en': 'Narsil/deberta-large-mnli-zero-cls', # English 'de': 'Sahajtomar/German_Zeroshot', # German 'es': 'Recognai/zeroshot_selectra_medium', # Spanish 'it': 'joeddav/xlm-roberta-large-xnli', # Italian 'ru': 'DeepPavlov/xlm-roberta-large-en-ru-mnli', # Russian 'tr': 'vicgalle/xlm-roberta-large-xnli-anli', # Turkish 'no': 'NbAiLab/nb-bert-base-mnli'} # Norsk hypothesis_templates = {'en': 'This example is {}.', # English 'de': 'Dieses beispiel ist {}.', # German 'es': 'Este ejemplo es {}.', # Spanish 'it': 'Questo esempio è {}.', # Italian 'ru': 'Этот пример {}.', # Russian 'tr': 'Bu örnek {}.', # Turkish 'no': 'Dette eksempelet er {}.'} # Norsk classifiers = {'en': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['en'], model=models['en']), 'de': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['de'], model=models['de']), 'es': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['es'], model=models['es']), 'it': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['it'], model=models['it']), 'ru': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['ru'], model=models['ru']), 'tr': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['tr'], model=models['tr']), 'no': pipeline("zero-shot-classification", hypothesis_template=hypothesis_templates['no'], model=models['no'])} fasttext_model = fasttext.load_model(hf_hub_download("julien-c/fasttext-language-id", "model.bin")) def prep_examples(): example_text1 = "Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. Most \ people who fall sick with COVID-19 will experience mild to moderate symptoms and recover without special treatment. \ However, some will become seriously ill and require medical attention." example_labels1 = "business,health related,politics,climate change" example_text2 = "Elephants are" example_labels2 = "big,small,strong,fast,carnivorous" example_text3 = "Elephants" example_labels3 = "are big,can be very small,generally not strong enough,are faster than you think" example_text4 = "Dogs are man's best friend" example_labels4 = "positive,negative,neutral" example_text5 = "Amar sonar bangla ami tomay bhalobasi" example_labels5 = "bhalo,kharap" example_text6 = "Letzte Woche gab es einen Selbstmord in einer nahe gelegenen kolonie" example_labels6 = "verbrechen,tragödie,stehlen" example_text7 = "El autor se perfila, a los 50 años de su muerte, como uno de los grandes de su siglo" example_labels7 = "cultura,sociedad,economia,salud,deportes" example_text8 = "Россия в среду заявила, что военные учения в аннексированном Москвой Крыму закончились \ и что солдаты возвращаются в свои гарнизоны, на следующий день после того, как она объявила о первом выводе \ войск от границ Украины." example_labels8 = "новости,комедия" example_text9 = "I quattro registi - Federico Fellini, Pier Paolo Pasolini, Bernardo Bertolucci e Vittorio De Sica - \ hanno utilizzato stili di ripresa diversi, ma hanno fortemente influenzato le giovani generazioni di registi." example_labels9 = "cinema,politica,cibo" example_text10 = "Ja, vi elsker dette landet,\ som det stiger frem,\ furet, værbitt over vannet,\ med de tusen hjem.\ Og som fedres kamp har hevet\ det av nød til seir" example_labels10 = "helse,sport,religion,mat,patriotisme og nasjonalisme" example_text11 = "Şampiyonlar Ligi’nde 5. hafta oynanan karşılaşmaların ardından sona erdi. Real Madrid, \ Inter ve Sporting oynadıkları mücadeleler sonrasında Son 16 turuna yükselmeyi başardı. \ Gecenin dev mücadelesinde ise Manchester City, PSG’yi yenerek liderliği garantiledi." example_labels11 = "dünya,ekonomi,kültür,siyaset,spor,teknoloji" examples = [ [example_text1, example_labels1], [example_text2, example_labels2], [example_text3, example_labels3], [example_text4, example_labels4], [example_text5, example_labels5], [example_text6, example_labels6], [example_text7, example_labels7], [example_text8, example_labels8], [example_text9, example_labels9], [example_text10, example_labels10], [example_text11, example_labels11]] return examples def detect_lang(sequence, labels): DetectorFactory.seed = 0 seq_lang = 'en' try: # seq_lang = detect(sequence) # lbl_lang = detect(labels) seq_lang = fasttext_model.predict(sequence)[0][0].split("__label__")[1] lbl_lang = fasttext_model.predict(labels)[0][0].split("__label__")[1] except: print("Language detection failed!", "Date:{}, Sequence:{}, Labels:{}".format( str(datetime.datetime.now()), labels)) if seq_lang != lbl_lang: print("Different languages detected for sequence and labels!", "Date:{}, Sequence:{}, Labels:{}, Sequence Language:{}, Label Language:{}".format( str(datetime.datetime.now()), sequence, labels, seq_lang, lbl_lang)) if seq_lang in models: print("Sequence Language detected.", "Date:{}, Sequence:{}, Sequence Language:{}".format( str(datetime.datetime.now()), sequence, seq_lang)) else: print("Language not supported. Defaulting to English!", "Date:{}, Sequence:{}, Sequence Language:{}".format( str(datetime.datetime.now()), sequence, seq_lang)) seq_lang = 'en' return seq_lang def sequence_to_classify(sequence, labels): classifier = classifiers[detect_lang(sequence, labels)] label_clean = str(labels).split(",") response = classifier(sequence, label_clean, multi_label=True) predicted_labels = response['labels'] predicted_scores = response['scores'] clean_output = {idx: float(predicted_scores.pop(0)) for idx in predicted_labels} print("Date:{}, Sequence:{}, Labels: {}".format( str(datetime.datetime.now()), sequence, predicted_labels)) return clean_output iface = gr.Interface( title="Multilingual Multi-label Zero-shot Classification", description="Currently supported languages are English, German, Spanish, Italian, Russian, Turkish, Norsk.", fn=sequence_to_classify, inputs=[gr.inputs.Textbox(lines=10, label="Please enter the text you would like to classify...", placeholder="Text here..."), gr.inputs.Textbox(lines=2, label="Possible candidate labels (separated by comma)...", placeholder="Labels here separated by comma...")], outputs=gr.outputs.Label(num_top_classes=5), capture_session=True, #interpretation="default", examples=prep_examples()) iface.launch()