from pathlib import Path from functools import partial from joeynmt.prediction import predict from joeynmt.helpers import ( check_version, load_checkpoint, load_config, parse_train_args, resolve_ckpt_path, ) from joeynmt.model import build_model from joeynmt.tokenizers import build_tokenizer from joeynmt.vocabulary import build_vocab from joeynmt.datasets import build_dataset import gradio as gr languages_scripts = { "Azeri Turkish in Persian": "AzeriTurkish-Persian", "Central Kurdish in Arabic": "Sorani-Arabic", "Central Kurdish in Persian": "Sorani-Persian", "Gilaki in Persian": "Gilaki-Persian", "Gorani in Arabic": "Gorani-Arabic", "Gorani in Central Kurdish": "Gorani-Sorani", "Gorani in Persian": "Gorani-Persian", "Kashmiri in Urdu": "Kashmiri-Urdu", "Mazandarani in Persian": "Mazandarani-Persian", "Northern Kurdish in Arabic": "Kurmanji-Arabic", "Northern Kurdish in Persian": "Kurmanji-Persian", "Sindhi in Urdu": "Sindhi-Urdu" } def normalize(text, language_script): cfg_file = "./models/%s/config.yaml"%languages_scripts[language_script] ckpt = "./models/%s/best.ckpt"%languages_scripts[language_script] cfg = load_config(Path(cfg_file)) # parse and validate cfg model_dir, load_model, device, n_gpu, num_workers, _, fp16 = parse_train_args( cfg["training"], mode="prediction") test_cfg = cfg["testing"] src_cfg = cfg["data"]["src"] trg_cfg = cfg["data"]["trg"] load_model = load_model if ckpt is None else Path(ckpt) ckpt = resolve_ckpt_path(load_model, model_dir) src_vocab, trg_vocab = build_vocab(cfg["data"], model_dir=model_dir) model = build_model(cfg["model"], src_vocab=src_vocab, trg_vocab=trg_vocab) # load model state from disk model_checkpoint = load_checkpoint(ckpt, device=device) model.load_state_dict(model_checkpoint["model_state"]) if device.type == "cuda": model.to(device) tokenizer = build_tokenizer(cfg["data"]) sequence_encoder = { src_cfg["lang"]: partial(src_vocab.sentences_to_ids, bos=False, eos=True), trg_cfg["lang"]: None, } test_cfg["batch_size"] = 1 # CAUTION: this will raise an error if n_gpus > 1 test_cfg["batch_type"] = "sentence" test_data = build_dataset( dataset_type="stream", path=None, src_lang=src_cfg["lang"], trg_lang=trg_cfg["lang"], split="test", tokenizer=tokenizer, sequence_encoder=sequence_encoder, ) test_data.set_item(text.strip()) cfg=test_cfg _, _, hypotheses, trg_tokens, trg_scores, _ = predict( model=model, data=test_data, compute_loss=False, device=device, n_gpu=n_gpu, normalization="none", num_workers=num_workers, cfg=cfg, fp16=fp16, ) return hypotheses[0] title = """ <center><strong><font size='8'>Script Normalization for Unconventional Writing<font></strong></center> <div align="center"> <img src="https://raw.githubusercontent.com/sinaahmadi/ScriptNormalization/main/Perso-Arabic_scripts.jpg" alt="Perso-Arabic scripts used by the target languages in our paper" width="400"> </div> <h3 style="font-weight: 450; font-size: 1rem; margin: 0rem"> [<a href="https://sinaahmadi.github.io/docs/articles/ahmadi2023acl.pdf" style="color:blue;">Paper (ACL 2023)</a>] [<a href="https://sinaahmadi.github.io/docs/slides/ahmadi2023acl_slides.pdf" style="color:blue;">Slides</a>] [<a href="https://github.com/sinaahmadi/ScriptNormalization" style="color:blue;">GitHub</a>] [<a href="https://s3.amazonaws.com/pf-user-files-01/u-59356/uploads/2023-06-04/rw32pwp/ACL2023.mp4" style="color:blue;">Presentation</a>] </h3> """ description = """ <ul> <li style="font-size:120%;">"<em>mar7aba!</em>"</li> <li style="font-size:120%;">"<em>هاو ئار یوو؟</em>"</li> <li style="font-size:120%;">"<em>Μπιάνβενου α σετ ντεμό!</em>"</li> </ul> <p style="font-size:120%;">What do all these sentences have in common? Being greeted in Arabic with "<em>mar7aba</em>" written in the Latin script, then asked how you are ("<em>هاو ئار یوو؟</em>") in English using the Perso-Arabic script of Kurdish and then, welcomed to this demo in French ("<em>Μπιάνβενου α σετ ντεμό!</em>") written in Greek script. All these sentences are written in an <strong>unconventional</strong> script.</p> <p style="font-size:120%;">Although you may find these sentences risible, unconventional writing is a common practice among millions of speakers in bilingual communities. In our paper entitled "<a href="https://sinaahmadi.github.io/docs/articles/ahmadi2023acl.pdf" target="_blank"><strong>Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities</strong></a>", we shed light on this problem and propose an approach to normalize noisy text written in unconventional writing.</p> <p style="font-size:120%;">This demo deploys a few models that are trained for <strong>the normalization of unconventional writing</strong>. Please note that this tool is not a spell-checker and cannot correct errors beyond character normalization. For better performance, you can apply hard-coded rules on the input and then pass it to the models, hence a hybrid system.</p> <p style="font-size:120%;">For more information, you can check out the project on GitHub too: <a href="https://github.com/sinaahmadi/ScriptNormalization" target="_blank"><strong>https://github.com/sinaahmadi/ScriptNormalization</strong></a></p> """ examples = [ ["بو شهرین نوفوسو ، 2014 نجی ایلين نوفوس ساییمی اساسيندا 41 نفر ایمیش .", "Azeri Turkish in Persian"],#"بۇ شهرین نۆفوسو ، 2014 نجی ایلين نۆفوس ساییمی اساسيندا 41 نفر ایمیش ." ["ياخوا تةمةن دريژبيت بوئةم ميللةتة", "Central Kurdish in Arabic"], ["یکیک له جوانیکانی ام شاره جوانه", "Central Kurdish in Persian"], ["نمک درهٰ مردوم گيلک ايسن ؤ اوشان زوان ني گيلکي ايسه .", "Gilaki in Persian"], ["شؤنةو اانةيةرة گةشت و گلي ناجارانةو اؤجالاني دةستش پنةكةرد", "Gorani in Arabic"], #شۆنەو ئانەیەرە گەشت و گێڵی ناچارانەو ئۆجالانی دەستش پنەکەرد ["ڕوٙو زوانی ئەذایی چەنی پەیذابی ؟", "Gorani in Central Kurdish"], # ڕوٙو زوانی ئەڎایی چەنی پەیڎابی ؟ ["هنگامکان ظميٛ ر چمان ، بپا کريٛلي بيشان :", "Gorani in Persian"], # هەنگامەکان وزمیٛ وەرو چەمان ، بەپاو کریٛڵی بیەشان : ["ربعی بن افکل اُسے اَکھ صُحابی .", "Kashmiri in Urdu"], # ربعی بن افکل ٲسؠ اَکھ صُحابی . ["اینتا زون گنشکرون 85 میلیون نفر هسن", "Mazandarani in Persian"], # اینتا زوون گِنِشکَرون 85 میلیون نفر هسنه ["بة رطكا هة صطئن ژ دل هاطة بة لافكرن", "Northern Kurdish in Arabic"], #پەرتوکا هەستێن ژ دل هاتە بەلافکرن ["ثرکى همرنگ نرميني دويت هندک قوناغين دي ببريت", "Northern Kurdish in Persian"], # سەرەکی هەمەرەنگ نەرمینێ دڤێت هندەک قوناغێن دی ببڕیت ["ہتی کجھ اپ ۽ تمام دائون ترینون بیھندیون آھن .", "Sindhi in Urdu"] # هتي ڪجھ اپ ۽ تمام ڊائون ٽرينون بيھنديون آھن . ] article = """ <div style="text-align: justify; max-width: 1200px; margin: 20px auto;"> <h3 style="font-weight: 450; font-size: 1rem; margin: 0rem"> <b>Created and deployed by Sina Ahmadi <a href="https://sinaahmadi.github.io/">(https://sinaahmadi.github.io/)</a>. </h3> </div> """ demo = gr.Interface( title=title, description=description, fn=normalize, inputs=[ gr.Textbox(lines=4, label="Noisy Text \U0001F974"), gr.Dropdown(label="Language in unconventional script", choices=sorted(list(languages_scripts.keys()))), ], outputs=gr.Textbox(label="Normalized Text \U0001F642"), examples=examples, article=article, examples_per_page=20, cache_examples=False ) demo.launch()