mmarron14/whisper-medium-cv17-es-5-steps_proc2-def3

Whisper Medium CV17 Es 5 steps with processing of text using method 2; with same configuration as 5-steps-sin_proc-def3: with filtering 30sec, and with customised optimizer- 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: 0.3280
• Wer Ortho: 12.4778
• Wer: 7.0640

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
• training_steps: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
No log	0.2	1	0.6498	12.5695	7.1054
No log	0.4	2	0.5543	12.3511	7.0297
No log	0.6	3	0.4379	12.3766	7.0215
No log	0.8	4	0.3593	12.4301	7.0355
No log	1.0	5	0.3280	12.4778	7.0640

Framework versions

• Transformers 4.53.2
• Pytorch 2.9.1+cu128
• Datasets 2.14.4
• Tokenizers 0.21.4