mmarron14/whisper-medium-cv17-es-50-steps

Whisper Medium CV17 Es 50 steps- María Marrón

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5798
• Wer Ortho: 11.4657
• Cer Ortho: 3.2862
• Wer: 6.9420
• Cer: 2.3005

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: 2
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 64
• 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: 5
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Cer Ortho	Wer	Cer
2.9481	0.2	10	1.7270	12.0729	3.6802	7.1193	2.5784
1.3731	0.4	20	1.0923	11.5624	3.3599	6.9948	2.3544
0.9897	0.6	30	0.8008	11.6923	3.3918	7.0571	2.3674
0.7372	0.8	40	0.6473	11.4720	3.3122	6.9293	2.3112
0.6275	1.0	50	0.5798	11.4657	3.2862	6.9420	2.3005

Framework versions

• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2