Hugging Face's logo

svanhvit
/
byt5-ocr-post-processing-faroese-ai-yfirlestur

Text2Text Generation
Transformers
PyTorch
Faroese
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
byt5-ocr-post-processing-faroese-ai-yfirlestur / README.md
svanhvit's picture
svanhvit
Update README.md
7c173c7
preview code
|
raw
history blame
757 Bytes
metadata
language: fo
tag: text2text-generation
pipeline_tag: text2text-generation
widget:
  - text: >-
      Lutfalsligá er vøksturin líka stórur á Suðuro)rar sjúkrahúsi, meðan ]ítil
      og ongin vøkstur er á Klaksvíkar sjúkráhúsi
inference:
  parameters:
    max_length: 512

Model Card for Model ID

OCR post processing for Faroese.

Model Details

This model is finetuned using a ByT5 model (base) trained to do Icelandic grammatical error correction: https://huggingface.co/mideind/yfirlestur-icelandic-correction-byt5

The Faroese training data was created by extracting authentic errors from OCR-ed Faroese texts and applied to a corpus of Faroese, along with random character noise.