AleksanderObuchowski/trainer_output

whisper-small-med-pl

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: 0.7463
• Wer: 44.2464

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_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_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8305	0.4954	108	0.8192	55.6976
0.7908	0.9908	216	0.7731	49.3476
0.7031	1.4862	324	0.7591	47.6053
0.6715	1.9817	432	0.7479	49.9371
0.6193	2.4771	540	0.7478	47.1537
0.6019	2.9725	648	0.7463	44.2464

Framework versions

• Transformers 4.51.3
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.21.4