finetune-new

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

• Loss: 0.7404
• Cer: 29.5162

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: 3e-06
• train_batch_size: 8
• eval_batch_size: 8
• 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: reduce_lr_on_plateau
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.5602	1.0	1262	0.6160	24.7346
0.4761	2.0	2524	0.6140	24.7332
0.4084	3.0	3786	0.6206	23.6285
0.3623	4.0	5048	0.6383	22.0688
0.3264	5.0	6310	0.6624	23.9800
0.3022	6.0	7572	0.6915	25.2344
0.291	7.0	8834	0.7153	28.1998
0.2677	8.0	10096	0.7404	29.5162

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu129
• Datasets 4.0.0
• Tokenizers 0.22.0