whisper-small-dga-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: 0.5492
• Wer: 0.3161
• Cer: 0.1394

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: 16
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
0.9446	1.0616	500	0.5402	0.3682	0.1602
0.6005	2.1231	1000	0.4691	0.3525	0.1484
0.4301	3.1847	1500	0.4568	0.3347	0.1457
0.2716	4.2463	2000	0.4856	0.3278	0.1417
0.1731	5.3079	2500	0.5215	0.3319	0.1440
0.1254	6.3694	3000	0.5492	0.3161	0.1394

Framework versions

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