| 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) |