whisper-small-yo-benin1

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1107
• Wer: 6.7908
• Bleu: 0.0134
• Chrf: 11.4677

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: 4e-06
• train_batch_size: 4
• eval_batch_size: 4
• 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: 25
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Bleu	Chrf
0.283	0.3322	100	0.4633	7.3241	0.0116	11.3183
0.2862	0.6645	200	0.3027	7.7977	0.0102	9.6242
0.2512	0.9967	300	0.1743	5.6621	0.0155	12.3981
0.0596	1.3289	400	0.1373	6.2046	0.0163	12.2453
0.0556	1.6611	500	0.1107	6.7908	0.0134	11.4677

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1