File size: 1,348 Bytes
c029068 4ca7d18 c029068 |
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 |
from transformers import MarianMTModel, MarianTokenizer
import spacy
import streamlit as st
nlp = spacy.load("./cycLingoNER")
nlp.add_pipe('sentencizer')
colors = {"cycLingo": "#F67DE3"}
options = {"colors": colors}
# Load NMT model
tokenizer = MarianTokenizer.from_pretrained('DanielHellebust/cyclingo')
model = MarianMTModel.from_pretrained("DanielHellebust/cyclingo")
st.title('cycLingo Translator')
st.markdown('Translate cycling specific text from English to Norwegian')
st.subheader('English:')
text = st.text_area('English',label_visibility='hidden', placeholder='Enter text to translate to Norwegian', height=200)
if st.button('Translate'):
text_list = text.split()
if len(text_list) > 100:
st.error('Please enter less than 100 words to get full translation')
translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True))
result = [tokenizer.decode(t, skip_special_tokens=True) for t in translated]
st.subheader('Detected cycLingo entities:')
doc = nlp(text)
html = spacy.displacy.render(doc, style="ent", options=options)
st.markdown(html, unsafe_allow_html=True)
st.markdown(' ')
# update textarea with result as value
st.subheader('Norwegian Translation:')
st.text_area('Norwegian Translation',label_visibility='hidden', value=result[0], height=200)
|