deepdml/whisper-base-ig-mix

Whisper Base ig

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

• Loss: 1.7179
• Wer: 93.3804

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: 8
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2396	0.2	1000	1.3704	57.7791
0.0803	1.0814	2000	1.5414	71.3104
0.0636	1.2814	3000	1.6047	94.5668
0.0346	2.1628	4000	1.6904	83.7003
0.035	3.0442	5000	1.7179	93.3804

Framework versions

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

Citation

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