metadata

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.

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 trained on spelling correction. It leans on the excellent work by Oliver Guhr (github, huggingface). 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 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:

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