whisper-base-yor-oct2-2025

This model is a fine-tuned version of LinguaSpanApp/whisper-base-yor-sep29-2025 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0162
• Wer: 0.7867

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: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0605	0.4655	500	0.0418	0.3895
0.0785	0.9311	1000	0.0361	0.5171
0.0666	1.3966	1500	0.0361	0.1514
0.0614	1.8622	2000	0.0339	0.1286
0.0478	2.3277	2500	0.0282	0.1114
0.0521	2.7933	3000	0.0302	0.1505
0.0446	3.2588	3500	0.0220	0.1943
0.0441	3.7244	4000	0.0195	0.1914
0.0363	4.1899	4500	0.0214	0.2448
0.0354	4.6555	5000	0.0162	0.7867

Framework versions

• Transformers 4.56.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.1