Bedru/whisper-small-wello

Whisper Small am - Bedru Yimam

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

• Loss: 0.2421
• Wer Ortho: 74.3127
• Wer: 72.7915

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: 16
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.3265	2.4631	500	0.4823	95.6186	94.3463
0.1231	4.9261	1000	0.2909	87.2852	86.0424
0.0340	7.3892	1500	0.2527	76.8900	76.5018
0.0274	9.8522	2000	0.2421	74.3127	72.7915

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2