yoruba_whisper

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

• Loss: 0.7232
• Wer: 75.4654

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_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8696	1.85	1000	0.8730	79.4692
0.6117	3.7	2000	0.7474	75.6604
0.5195	5.56	3000	0.7232	75.4654

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu118
• Datasets 2.16.1
• Tokenizers 0.15.0