whisper-small-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: 3.1654
• Wer: 77.7647

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.4232	1.0	50	2.4770	255.4118
1.1503	2.0	100	2.4865	322.2353
0.3783	3.0	150	2.6993	152.7059
0.2291	4.0	200	2.8199	79.7647
0.1285	5.0	250	3.1357	96.1176
0.0683	6.0	300	3.0312	110.8235
0.0597	7.0	350	3.1471	76.9412
0.0147	8.0	400	3.0947	84.7059
0.0026	9.0	450	3.1555	102.4706
0.0006	10.0	500	3.1654	77.7647

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0