---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bart-base-spelling-nl-1m-3
  results: []
language:
- nl
metrics:
- bleu
- cer
- wer
- meteor
pipeline_tag: text2text-generation
---

# 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 of human-corrected spelling
errors of Dutch snippets of internet text ([errors](https://huggingface.co/antalvdb/bart-base-spelling-nl/blob/main/opentaal-annotaties.txt.errors) 
and [corrections](https://huggingface.co/antalvdb/bart-base-spelling-nl/blob/main/opentaal-annotaties.txt.corrections), 
run [spell.py](https://huggingface.co/antalvdb/bart-base-spelling-nl/blob/main/spell.py))

* CER    - 0.024
* WER    - 0.088
* BLEU   - 0.840
* METEOR - 0.932

Note that it is very hard for any spelling corrector to clean more actual spelling errors 
than introducing new errors. In other words, most spelling correctors cannot be run
automatically and must be used interactively.

These are the upper-bound scores when correcting _nothing_. In other words, this is 
the actual distance between the errors and their corrections in the evaluation set:

* CER    - 0.010
* WER    - 0.053
* BLEU   - 0.900
* METEOR - 0.954

We are not there yet, clearly.

## 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 12,351,203 lines
of text, containing a total of 123,131,153 words, from three public Dutch sources, downloaded from the
[Opus corpus](https://opus.nlpl.eu/):

- nl-europarlv7.txt (2,387,000 lines)
- nl-opensubtitles2016.9m.txt (9,000,000 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