You can deploy this model and start earning money today!

comma-project/
normalization-byt5-small

Name: normalization-byt5-small
Rating: 2.5 (45 reviews)

safetensors

translation

comma-project/alignement-pairs

google/byt5-small

finetune

cc-by-4.0

Views

No views yet

ByT5-Small for Normalization

This models allows for normalization of ATR output using CATMuS guidelines, for both Latin and Old French. It fixes spacing, it has tendencies to overnormalize and add punctuation.

from transformers import pipeline
import unicodedata

pipe = pipeline(
    task="text2text-generation",  # change if needed
    model="comma-project/normalization-byt5-small",                  # local directory
    tokenizer="comma-project/normalization-byt5-small"
)
pipe(unicodedata.normalize("NFD", "Scͥbo uobiᷤᷤ ñ pauli ł donati. "))
# [{'generated_text': 'scribo uobis, non Pauli uel Donati''}]