| import torch | |
| # from utils import label_full_decoder | |
| # import sys | |
| # import dataset | |
| # import engine | |
| # from model import BERTBaseUncased | |
| # from tokenizer import tokenizer | |
| # import config | |
| from transformers import pipeline, AutoTokenizer, AutoModel | |
| import gradio as gr | |
| # DEVICE = config.device | |
| model = AutoModel.from_pretrained("thak123/bert-emoji-latvian-twitter-classifier") | |
| # 7 EPOCH Version | |
| BERT_PATH = "FFZG-cleopatra/bert-emoji-latvian-twitter" | |
| tokenizer = transformers.BertTokenizer.from_pretrained( | |
| BERT_PATH, | |
| do_lower_case=True | |
| ) | |
| #AutoTokenizer.from_pretrained("FFZG-cleopatra/bert-emoji-latvian-twitter") | |
| classifier = pipeline("sentiment-analysis", | |
| model= model, | |
| tokenizer = tokenizer) | |
| # MODEL = BERTBaseUncased() | |
| # MODEL.load_state_dict(torch.load(config.MODEL_PATH, map_location=torch.device(DEVICE))) | |
| # MODEL.eval() | |
| # T = tokenizer.TweetTokenizer( | |
| # preserve_handles=True, preserve_hashes=True, preserve_case=False, preserve_url=False) | |
| def preprocess(text): | |
| tokens = T.tokenize(text) | |
| print(tokens, file=sys.stderr) | |
| ptokens = [] | |
| for index, token in enumerate(tokens): | |
| if "@" in token: | |
| if index > 0: | |
| # check if previous token was mention | |
| if "@" in tokens[index-1]: | |
| pass | |
| else: | |
| ptokens.append("mention_0") | |
| else: | |
| ptokens.append("mention_0") | |
| else: | |
| ptokens.append(token) | |
| print(ptokens, file=sys.stderr) | |
| return " ".join(ptokens) | |
| def sentence_prediction(sentence): | |
| # sentence = preprocess(sentence) | |
| # model_path = config.MODEL_PATH | |
| # test_dataset = dataset.BERTDataset( | |
| # review=[sentence], | |
| # target=[0] | |
| # ) | |
| # test_data_loader = torch.utils.data.DataLoader( | |
| # test_dataset, | |
| # batch_size=config.VALID_BATCH_SIZE, | |
| # num_workers=3 | |
| # ) | |
| # device = config.device | |
| # model = BERTBaseUncased() | |
| # # model.load_state_dict(torch.load( | |
| # # model_path, map_location=torch.device(device))) | |
| # model.to(device) | |
| # outputs, [] = engine.predict_fn(test_data_loader, MODEL, device) | |
| outputs = classifier(sentence) | |
| print(outputs) | |
| return outputs #{"label":outputs[0]} | |
| # demo = gr.Interface( | |
| # fn=sentence_prediction, | |
| # inputs=gr.Textbox(placeholder="Enter a sentence here..."), | |
| # outputs="label", | |
| # interpretation="default", | |
| # examples=[["!"]]) | |
| # demo.launch() | |
| # gr.Interface(fn=sentence_prediction,inputs="text",outputs="label").launch() | |
| # def greet(name): | |
| # return "Hello " + name + "!" | |
| # demo = gr.Interface( | |
| # fn=greet, | |
| # inputs=gr.Textbox(lines=2, placeholder="Name Here..."), | |
| # outputs="text", | |
| # ) | |
| # demo.launch() | |
| # import gradio as gr | |
| # from transformers import pipeline | |
| # pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-en-es") | |
| def predict(text): | |
| return pipe(text)[0]["translation_text"] | |
| demo = gr.Interface( | |
| fn=sentence_prediction, | |
| inputs='text', | |
| outputs='label', | |
| ) | |
| demo.launch() | |