File size: 482 Bytes
d07b900
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
import streamlit as st

from transformers import AutoModelForMaskedLM
from transformers import AutoTokenizer, FillMaskPipeline
from pprint import pprint
tokenizer_hf = AutoTokenizer.from_pretrained('projecte-aina/roberta-base-ca-v2')
model = AutoModelForMaskedLM.from_pretrained('projecte-aina/roberta-base-ca-v2')
model.eval()
pipeline = FillMaskPipeline(model, tokenizer_hf)
text = f"Em dic <mask>."
res_hf = pipeline(text)
pprint([r['token_str'] for r in res_hf])

st.write(text)