Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import tensorflow as tf | |
| from tensorflow import keras | |
| import keras_nlp | |
| import PyPDF2 | |
| import docx2txt | |
| hf_username = huggingface_hub.whoami()['name'] | |
| hf_url = f'hf://{hf_username}/bart_billsum' | |
| # Load your Keras model | |
| def load_model_and_preprocessor(): | |
| bart_billsum = keras_nlp.models.BartSeq2SeqLM.from_preset(f'hf://{hf_username}/bart_billsum') | |
| # Load the default BART preprocessor (assuming you saved its configuration) | |
| #preprocessor = keras_nlp.models.BartSeq2SeqLMPreprocessor.from_preset('bart_base_en', encoder_sequence_length=512, | |
| #decoder_sequence_length=128,) | |
| return model | |
| model = load_model_and_preprocessor() | |
| st.title("SummarizeIt") | |
| # File uploader | |
| uploaded_file = st.file_uploader("Choose a file", type=["pdf", "txt", "docx"]) | |
| # Text extraction | |
| text = "" | |
| if uploaded_file is not None: | |
| if uploaded_file.type == "application/pdf": | |
| pdf_reader = PyPDF2.PdfReader(uploaded_file) | |
| for page in pdf_reader.pages: | |
| text += page.extract_text() | |
| elif uploaded_file.type == "text/plain": | |
| text = uploaded_file.read().decode("utf-8") | |
| elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document": | |
| text = docx2txt.process(uploaded_file) | |
| # Text input for direct text entry | |
| user_input = st.text_area("Or paste your text here:") | |
| text = user_input if user_input else text # Prioritize user input over file | |
| def generate_text(model, input_texts, max_length=200, print_time_taken=False): | |
| # Convert input_texts to a list if it's a Dataset | |
| if isinstance(input_texts, datasets.Dataset): | |
| input_texts = input_texts.to_list() | |
| chunks = [input_texts[i:i+512] for i in range(0, len(input_texts), 512)] | |
| #initialize an empty list to store summaries | |
| summaries = [] | |
| # generate summaries for each chunk | |
| for chunk in chunks: | |
| # Assuming your model's generate method can handle a batch of inputs | |
| summary = model.generate(input_texts, max_length=max_length) | |
| summaries.append(summary) | |
| return summary | |
| generated_summaries = generate_text( | |
| model, | |
| text, # Pass the list of documents directly | |
| ) | |
| st.subheader("Generated Summary:") | |
| st.write(summary) |