mmarron14/whisper-medium-cv17-es-5-steps_sin_proc-def4

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Whisper Medium CV17 Es 5 steps without processing of text -same configuration of training as 5-stepssinproc, but with filtering 30sec- 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: 0.3184
• —Wer Ortho: 12.5020
• —Wer: 7.0621

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
• —trainbatchsize: 2
• —evalbatchsize: 4
• —seed: 42
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 64
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —training_steps: 5
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

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