import numpy as np import pdf2image import gradio as gr from imports import * from huggingface_hub import login login(token="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") device = torch.device("cuda" if torch.cuda.is_available() else "cpu") dict_ = { 0: "negative", 1: "positive", 2: "neutral"} tokenizer_sent = AutoTokenizer.from_pretrained("nam194/sentiment", use_fast=False) model_sent = AutoModelForSequenceClassification.from_pretrained("nam194/sentiment", num_labels=3, use_auth_token=True).to(device) def cvt2cls(data): data = list(set(data)) try: data.remove(20) except: pass for i, num in enumerate(data): if num == 20: continue if num>=10: data[i] -= 10 return data ner_tags = {0: 'B-chỗ để xe', 1: 'B-con người', 2: 'B-công việc', 3: 'B-cơ sở vật chất', 4: 'B-dự án', 5: 'B-lương', 6: 'B-môi trường làm việc', 7: 'B-ot/thời gian', 8: 'B-văn phòng', 9: 'B-đãi ngộ', 10: 'I-chỗ để xe', 11: 'I-con người', 12: 'I-công việc', 13: 'I-cơ sở vật chất', 14: 'I-dự án', 15: 'I-lương', 16: 'I-môi trường làm việc', 17: 'I-ot/thời gian', 18: 'I-văn phòng', 19: 'I-đãi ngộ', 20: 'O'} topic_tags = {0: 'chỗ để xe', 1: 'con người', 2: 'công việc', 3: 'cơ sở vật chất', 4: 'dự án', 5: 'lương', 6: 'môi trường làm việc', 7: 'ot/thời gian', 8: 'văn phòng', 9: 'đãi ngộ'} config = RobertaConfig.from_pretrained("nam194/ner", num_labels=21) tokenizer_topic = AutoTokenizer.from_pretrained("nam194/ner", use_fast=False) model_topic = PhoBertLstmCrf.from_pretrained("nam194/ner", config=config, from_tf=False).to(device) model_topic.resize_token_embeddings(len(tokenizer_topic)) def sentiment(sent: str): sent_ = normalize(text=sent) # segment input sentence, maybe raise ConnectionError: HTTPConnectionPool()) input_sent = torch.tensor([tokenizer_sent.encode(sent_)]).to(device) with torch.no_grad(): out_sent = model_sent(input_sent) logits_sent = out_sent.logits.softmax(dim=-1).tolist()[0] pred_sent = dict_[np.argmax(logits_sent)] sent = replace_all(text=sent) # segment input sentence, maybe raise ConnectionError: HTTPConnectionPool()) sent_segment = sent.split(".") for i, s in enumerate(sent_segment): s = s.strip() sent_segment[i] = underthesea.word_tokenize(s, format="text").split() dump = [[i, 'O'] for s in sent_segment for i in s] dump_set = NerDataset(feature_for_phobert([dump], tokenizer=tokenizer_topic, use_crf=True)) dump_iter = DataLoader(dump_set, batch_size=1) with torch.no_grad(): for idx, batch in enumerate(dump_iter): batch = { k:v.to(device) for k, v in batch.items() } outputs = model_topic(**batch) pred_topic = list(set([topic_tags[i] for i in cvt2cls(outputs["tags"][0])])) return "Sentiment: " + pred_sent + "\n" + "Topic in sentence: " + ". ".join([i.capitalize() for i in pred_topic]) # str({"sentiment": pred_sent, "topic": pred_topic}) def pdf_to_imgs(pdf): path_to_pdf = pdf.name # convert PDF to PIL images (one image by page) first_page = True # we want here only the first page as image if first_page: last_page = 1 else: last_page = None imgs = pdf2image.convert_from_path(path_to_pdf, last_page=last_page) return np.array(imgs[0]) with gr.Blocks() as demo: gr.Markdown("Demo projects Review Company and Resume parser phase 1.") with gr.Tab("Review Company"): text_input = gr.Textbox(label="Input sentence (ex: Sếp tốt, bảo hiểm đóng full lương bảo hiểm cho nhân viên. Hàng năm tăng lương ổn OT không trả thêm tiền, chỉ cho ngày nghỉ và hỗ trợ ăn tối.):", placeholder="input here...") text_output = gr.Textbox(label="Result:") text_button = gr.Button("Predict") with gr.Tab("Extract infomation from resume"): with gr.Row(): file_input = gr.File(label="PDF", file_types=[".pdf"]) image_output = gr.Image(type="numpy", label="Image of the first page") image_button = gr.Button("Predict") # with gr.Accordion("Open for More!"): # gr.Markdown("Look at me...") text_button.click(sentiment, inputs=text_input, outputs=text_output) image_button.click(pdf_to_imgs, inputs=file_input, outputs=image_output) demo.launch()