benjaminogbonna/whisper-tiny-igbo

Whisper Tiny Igbo - Benjamin Ogbonna

This model is a fine-tuned version of openai/whisper-tiny on the Whisper for Igbo 1.0 dataset. It achieves the following results on the evaluation set:

• Loss: 5.9958
• Wer: 100.0

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 25
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	50.0	50	4.6220	100.0
0.0	100.0	100	5.1929	105.7143
0.0	150.0	150	5.5613	108.5714
0.0	200.0	200	5.8296	97.1429
0.0	250.0	250	5.9560	100.0
0.0	300.0	300	5.9958	100.0

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1