deepdml/whisper-tiny-af-norm

Whisper Tiny af

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

• Loss: 1.7371
• Wer: 54.1818
• Cer: 22.4057

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: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.04
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0044	58.0028	1000	1.5109	50.4935	20.3296
0.0013	117.0022	2000	1.6154	53.9740	22.1681
0.0007	176.0016	3000	1.6788	54.0260	22.3353
0.0004	235.001	4000	1.7219	52.7965	21.8954
0.0004	294.0004	5000	1.7371	54.1818	22.4057

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1

Citation

Please cite the model using the following BibTeX entry:

@misc{deepdml/whisper-tiny-af-mix-norm,
      title={Fine-tuned Whisper tiny ASR model for speech recognition in Afrikaans},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-tiny-af-mix-norm}},
      year={2026}
    }