Be-win/whisper-small-ml-en-finetuned

whisper-small-finetuned-ml-en

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: 1.6611
• Wer: 153.5124

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.5079	1.4327	500	1.7015	114.2188
1.0223	2.8653	1000	1.5594	120.3721
0.4114	4.2980	1500	1.6128	154.1043
0.257	5.7307	2000	1.6611	153.5124

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.1.0
• Tokenizers 0.22.0