deepdml/whisper-large-v3-turbo-af-fleurs-norm

Whisper Turbo af

This model is a fine-tuned version of deepdml/whisper-large-v3-turbo on the Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.6276
• Wer: 22.0087
• Cer: 7.7354

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: 16
• eval_batch_size: 16
• 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: 600

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.27	0.1667	100	0.5701	29.3680	12.3977
0.0978	1.1183	200	0.5989	22.4416	8.0286
0.043	2.07	300	0.6077	26.3030	10.8378
0.026	3.0217	400	0.6073	23.4459	8.1606
0.0137	3.1883	500	0.6246	21.5931	7.6152
0.0069	4.14	600	0.6276	22.0087	7.7354

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-large-v3-turbo-af-fleurs-norm,
      title={Fine-tuned Whisper turbo ASR model for speech recognition in Afrikaans},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-large-v3-turbo-af-fleurs-norm}},
      year={2026}
    }