Downloads · 30 days
539
0% of all-time downloads
j5ng/et5-typos-corrector
et5-typos-corrector is a text generation model from j5ng. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- ETRI-et5 모델을 기반으로 fine-tuning한 한국어 구어체 전용 맞춤법 교정기 입니다.
Downloads · 30 days
539
0% of all-time downloads
All-time downloads
115K
Public
Repo size
3.9 GB
Likes
15
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
from transformers import T5ForConditionalGeneration, T5Tokenizer
# T5 모델 로드
model = T5ForConditionalGeneration.from_pretrained("j5ng/et5-typos-corrector")
tokenizer = T5Tokenizer.from_pretrained("j5ng/et5-typos-corrector")
device = "cuda:0" if torch.cuda.is_available() else "cpu"
# device = "mps:0" if torch.cuda.is_available() else "cpu" # for mac m1
model = model.to(device)
# 예시 입력 문장
input_text = "아늬 진짜 무ㅓ하냐고"
# 입력 문장 인코딩
input_encoding = tokenizer("맞춤법을 고쳐주세요: " + input_text, return_tensors="pt")
input_ids = input_encoding.input_ids.to(device)
attention_mask = input_encoding.attention_mask.to(device)
# T5 모델 출력 생성
output_encoding = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
max_length=128,
num_beams=5,
early_stopping=True,
)
# 출력 문장 디코딩
output_text = tokenizer.decode(output_encoding[0], skip_special_tokens=True)
# 결과 출력
print(output_text) # 아니 진짜 뭐 하냐고.
from transformers import T5ForConditionalGeneration, T5Tokenizer, pipeline
model = T5ForConditionalGeneration.from_pretrained('j5ng/et5-typos-corrector')
tokenizer = T5Tokenizer.from_pretrained('j5ng/et5-typos-corrector')
typos_corrector = pipeline(
"text2text-generation",
model=model,
tokenizer=tokenizer,
device=0 if torch.cuda.is_available() else -1,
framework="pt",
)
input_text = "완죤 어이업ㅅ네진쨬ㅋㅋㅋ"
output_text = typos_corrector("맞춤법을 고쳐주세요: " + input_text,
max_length=128,
num_beams=5,
early_stopping=True)[0]['generated_text']
print(output_text) # 완전 어이없네 진짜 ᄏᄏᄏᄏ.