whisper-small-ewe-gbotemi

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: 0.4834
• Wer: 0.3440
• Cer: 0.1173

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: 32
• eval_batch_size: 64
• 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
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.4260	0.5139	500	0.4562	0.3744	0.1305
0.2637	1.0277	1000	0.4141	0.3348	0.1127
0.2499	1.5416	1500	0.4145	0.3420	0.1200
0.1339	2.0555	2000	0.4662	0.3460	0.1173
0.1348	2.5694	2500	0.4834	0.3440	0.1173

Framework versions

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