README.md

---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bart-base-spelling-nl-1m-3
  results: []
---

# bart-base-spelling-nl

This model is a Dutch fine-tuned version of
[facebook/bart-base](https://huggingface.co/facebook/bart-base).

It achieves the following results on an external evaluation set:

* CER    - 0.025
* WER    - 0.090
* BLEU   - 0.837
* METEOR - 0.932


## Model description

This is a fine-tuned version of
[facebook/bart-base](https://huggingface.co/facebook/bart-base)
trained on spelling correction. It leans on the excellent work by
Oliver Guhr ([github](https://github.com/oliverguhr/spelling),
[huggingface](https://huggingface.co/oliverguhr/spelling-correction-english-base)). Training
was performed on an AWS EC2 instance (g5.xlarge) on a single GPU, and
took about two days.

## Intended uses & limitations

The intended use for this model is to be a component of the
[Valkuil.net](https://valkuil.net) context-sensitive spelling
checker. 

## Training and evaluation data

The model was trained on a Dutch dataset composed of 6,351,203 lines
of text from three public Dutch sources, downloaded from the
[Opus corpus](https://opus.nlpl.eu/):

- nl-europarlv7.txt (2,387,000 lines)
- nl-opensubtitles2016.3m.txt (3,000,000 lines)
- nl-wikipedia.txt (964,203 lines)


## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0


### Framework versions

- Transformers 4.27.3
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2