CoolFace
Modelpublic

zuazo/whisper-medium-es

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes20downloads
Model Card

<!-- 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 Spanish

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/commonvoice13_0 es dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1915
  • Wer: 5.4088

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: 64
  • evalbatchsize: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lrschedulertype: linear
  • lrschedulerwarmup_steps: 500
  • training_steps: 10000

Training results

Training LossEpochStepValidation LossWer
0.09172.010000.19446.8560
0.09274.020000.18176.1439
0.04566.0130000.18056.2626
0.03438.0140000.20976.1773
0.004610.0150000.22925.9374
0.082912.0160000.18146.0644
0.002114.0170000.23185.7096
0.028816.0180000.18715.5755
0.129718.0290000.18315.6885
0.037720.02100000.19155.4088

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3

Citation

If you use these models in your research, please cite:

bibtex
@misc{dezuazo2025whisperlmimprovingasrmodels,
      title={Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages}, 
      author={Xabier de Zuazo and Eva Navas and Ibon Saratxaga and Inma Hernáez Rioja},
      year={2025},
      eprint={2503.23542},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2503.23542}, 
}

Please, check the related paper preprint in arXiv:2503.23542 for more details.

Licensing

This model is available under the Apache-2.0 License. You are free to use, modify, and distribute this model as long as you credit the original creators.