This model is a fine-tuned version of abiyo27/whisper-small-ewe-2 on the Leonel-Maia/ewe_dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.4080
Wer: 0.3638

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: 1
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 60.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5044	0.4398	500	0.5129	0.4258
0.4169	0.8796	1000	0.4449	0.3849
0.3702	1.3193	1500	0.4213	0.3744
0.3679	1.7591	2000	0.4080	0.3638
0.2763	2.1988	2500	0.4142	0.3697
0.2764	2.6386	3000	0.4091	0.3615
0.183	3.0783	3500	0.4217	0.3648

Framework versions

Transformers 4.50.3
Pytorch 2.7.0+cu126
Datasets 3.5.0
Tokenizers 0.21.1

Leonel-Maia/whisper-small-bible

whisper-small-bible

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Leonel-Maia/
whisper-small-bible