HiTZ/whisper-base-gl

Whisper Base Galician

This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_13_0 gl dataset. It achieves the following results on the evaluation set:

• Loss: 0.4360
• Wer: 17.2910

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: 2.5e-05
• train_batch_size: 128
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.372	10.0	1000	0.4173	21.0023
0.1352	20.0	2000	0.3982	18.3620
0.0638	30.0	3000	0.4175	17.8842
0.0371	40.0	4000	0.4310	17.4721
0.0279	50.0	5000	0.4360	17.2910

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1

Citation

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

@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.