TopSlayer/whisper-small-lo

Whisper Small Lo - TopSlayer

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4486
• Wer: 27.3973

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: 5
• eval_batch_size: 8
• 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0071	20.8333	1000	0.3643	43.8356
0.0013	41.6667	2000	0.3832	36.9863
0.0	62.5	3000	0.4228	27.3973
0.0	83.3333	4000	0.4416	27.3973
0.0	104.1667	5000	0.4486	27.3973

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0