Spaces:
Sleeping
Sleeping
File size: 1,954 Bytes
4f8c634 4c05ba5 4f8c634 e89cc5c 4f8c634 e89cc5c 4f8c634 e89cc5c 4f8c634 e89cc5c 4f8c634 e89cc5c 4f8c634 e89cc5c 4f8c634 e89cc5c 4f8c634 e89cc5c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import streamlit as st
from transformers import T5Tokenizer, T5ForConditionalGeneration
from pdfminer.high_level import extract_text
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-small")
model = T5ForConditionalGeneration.from_pretrained("t5-small")
# Define translation prefixes for each language
translation_prefixes = {
"german": "translate English to German: ",
"french": "translate English to French: "
}
# Generate translations for each language
translations = {}
# Buttons to trigger translation
translate_german = st.button("Translate to German")
translate_french = st.button("Translate to French")
for language, prefix in translation_prefixes.items():
# Translate the entire text, not page by page
text_to_translate = prefix + text
input_ids = tokenizer(text_to_translate, return_tensors="pt").input_ids
outputs = model.generate(input_ids=input_ids, max_length=150, num_beams=4, no_repeat_ngram_size=2)
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
translations[language] = translated_text
# Display the translations based on the button clicked
if translate_german:
display_translation(translations["german"], "German")
if translate_french:
display_translation(translations["french"], "French")
def display_translation(translation, language):
st.write(f"\nLanguage: {language}")
st.write(f"Translation: {translation}")
if __name__ == "__main__":
main()
|