whisper-medium-espaniol

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

• Loss: 0.4883
• Wer: 11.4190

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2124	1.8692	1000	0.3589	12.5527
0.0308	3.7383	2000	0.4321	12.7264
0.0035	5.6075	3000	0.4681	11.7641
0.0011	7.4766	4000	0.4883	11.4190

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.2