| import torch | |
| from transformers import PegasusForConditionalGeneration, PegasusTokenizer, AutoTokenizer, AutoModelForSeq2SeqLM | |
| model_name = 'geckos/pegasus-fined-tuned-on-paraphrase' | |
| torch_device = 'cuda' if torch.cuda.is_available() else 'cpu' | |
| tokenizer = PegasusTokenizer.from_pretrained(model_name) | |
| model = PegasusForConditionalGeneration.from_pretrained(model_name).to(torch_device) | |
| def get_response(input_text,num_return_sequences): | |
| batch = tokenizer.prepare_seq2seq_batch([input_text],truncation=True,padding='longest',max_length=60, return_tensors="pt").to(torch_device) | |
| translated = model.generate(**batch,max_length=60,num_beams=4, num_return_sequences=num_return_sequences, temperature=0.5) | |
| tgt_text = tokenizer.batch_decode(translated, skip_special_tokens=True) | |
| return tgt_text | |
| from sentence_splitter import SentenceSplitter, split_text_into_sentences | |
| splitter = SentenceSplitter(language='en') | |
| def paraphraze(text): | |
| sentence_list = splitter.split(text) | |
| paraphrase = [] | |
| for i in sentence_list: | |
| a = get_response(i,1) | |
| paraphrase.append(a) | |
| paraphrase2 = [' '.join(x) for x in paraphrase] | |
| paraphrase3 = [' '.join(x for x in paraphrase2) ] | |
| paraphrased_text = str(paraphrase3).strip('[]').strip("'") | |
| return paraphrased_text | |
| import gradio as gr | |
| def summarize(text): | |
| paraphrased_text = paraphraze(text) | |
| return paraphrased_text | |
| gr.Interface(fn=summarize, inputs=gr.inputs.Textbox(lines=7, placeholder="Enter text here"), outputs=[gr.outputs.Textbox(label="Paraphrased Text")],examples=[["My Geckhos." | |
| ]]).launch(inline=False) |