This model is a fine-tuned version of openai/whisper-small on the IoanaLiviaPopescu/RealVoiceSynthVoice-800-1-Mixed-Standard-B-Wavnet-B dataset. It achieves the following results on the evaluation set:

Loss: 0.4100
Wer: 18.6797

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: 32
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0	0	0.6024	27.8812
0.5049	1.0	13	0.4971	19.9889
0.3055	2.0	26	0.4351	20.1918
0.1979	3.0	39	0.4137	19.1223
0.1439	4.0	52	0.4080	18.9747
0.119	5.0	65	0.4100	18.6797

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1