deepdml/whisper-small-ig-mix-norm

Whisper Small ig

This model is a fine-tuned version of openai/whisper-small on the google/fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 1.0158
• Wer: 45.3817
• Cer: 15.2871

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: 64
• 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_ratio: 0.04
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0942	0.2	1000	0.7792	47.9811	16.6628
0.023	1.0814	2000	0.9155	45.9453	15.5336
0.0243	1.2814	3000	0.9415	45.5274	15.3905
0.0068	2.1628	4000	0.9908	45.2456	15.2179
0.0055	3.0442	5000	1.0158	45.3817	15.2871

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-small-ig-mix-norm,
      title={Fine-tuned Whisper small ASR model for speech recognition in Lingala},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-small-ig-mix-norm}},
      year={2025}
    }