You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Whisper Small Icelandic

This model is a fine-tuned version of openai/whisper-small on the google/fleurs is_is dataset. It achieves the following results on the evaluation set:

Loss: 1.6747
Wer: 66.5053

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 64
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0002	499.0	1000	1.6747	66.5053
0.0001	999.0	2000	1.7714	67.6670
0.0	1499.0	3000	1.8178	68.6350

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.8.1.dev0
Tokenizers 0.13.2

Downloads last month: -

Dataset used to train arun100/whisper-small-is_is

Evaluation results

Wer on google/fleurs is_is
test set self-reported

66.505