|
--- |
|
language: |
|
- pt |
|
--- |
|
|
|
``` python |
|
|
|
from transformers import ElectraForPreTraining, ElectraTokenizerFast |
|
import torch |
|
|
|
discriminator = ElectraForPreTraining.from_pretrained("josu/electra-pt-br-small-discirminator") |
|
tokenizer = ElectraTokenizerFast.from_pretrained("josu/electra-pt-br-small-discirminator") |
|
|
|
sentence = "os passaros estão cantando" |
|
fake_sentence = "os passaros estão falando" |
|
|
|
fake_tokens = tokenizer.tokenize(fake_sentence) |
|
fake_inputs = tokenizer.encode(fake_sentence, return_tensors="pt") |
|
discriminator_outputs = discriminator(fake_inputs) |
|
predictions = torch.round((torch.sign(discriminator_outputs[0]) + 1) / 2) |
|
|
|
[print("%7s" % token, end="") for token in fake_tokens] |
|
|
|
[print("%7s" % int(prediction), end="") for prediction in predictions.squeeze().tolist() |
|
|
|
``` |
