whisper-small-am_on_aggregated

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

• Loss: 0.3521
• Wer: 59.7259

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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: 150
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6348	1.0	949	0.3261	72.4829
0.5115	2.0	1898	0.2721	66.8424
0.4417	3.0	2847	0.2869	66.9478
0.3545	4.0	3796	0.3172	60.5693
0.2887	5.0	4745	0.3521	59.7259

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0