Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import T5Tokenizer, T5ForConditionalGeneration | |
| from pdfminer.high_level import extract_text | |
| import nltk | |
| from nltk import sent_tokenize | |
| # Download the punkt tokenizer for sentence segmentation | |
| nltk.download('punkt') | |
| def main(): | |
| st.title("PDF Translation") | |
| # Upload the pdf | |
| uploaded_file = st.file_uploader("Upload a PDF file and we will translate the text inside to German and French", type=["pdf"]) | |
| if uploaded_file is not None: | |
| # Extract text from pdf | |
| text = extract_text(uploaded_file) | |
| tokenizer = T5Tokenizer.from_pretrained("t5-base") | |
| model = T5ForConditionalGeneration.from_pretrained("t5-base") | |
| # Define translation prefixes for each language | |
| translation_prefixes = { | |
| "german": "translate English to German: ", | |
| "french": "translate English to French: " | |
| } | |
| # Variables to track translation state | |
| translated_german = False | |
| translated_french = False | |
| # Buttons to trigger translation | |
| translate_german = st.button("Translate to German") | |
| translate_french = st.button("Translate to French") | |
| # Translate and display for German | |
| if translate_german and not translated_german: | |
| translated_sentences_german = translate_text(text, translation_prefixes["german"], tokenizer, model) | |
| display_translation(translated_sentences_german, "German") | |
| translated_german = True | |
| # Translate and display for French | |
| if translate_french and not translated_french: | |
| translated_sentences_french = translate_text(text, translation_prefixes["french"], tokenizer, model) | |
| display_translation(translated_sentences_french, "French") | |
| translated_french = True | |
| def translate_text(text, prefix, tokenizer, model): | |
| # Split text into sentences | |
| sentences = sent_tokenize(text) | |
| # Translate each sentence | |
| translated_sentences = [] | |
| for sentence in sentences: | |
| text_to_translate = prefix + sentence | |
| input_ids = tokenizer(text_to_translate, return_tensors="pt").input_ids | |
| outputs = model.generate(input_ids=input_ids, max_length=500, num_beams=4, no_repeat_ngram_size=2) | |
| translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| translated_sentences.append(translated_text) | |
| return translated_sentences | |
| def display_translation(translations, language): | |
| st.write(f"\nLanguage: {language}") | |
| st.write(f"Translation:\n {' '.join(translations)}") | |
| if __name__ == "__main__": | |
| main() | |