Setosm/whisper-base-afri

Whisper Base Afri

This model is a fine-tuned version of openai/whisper-base on the Afrispeech-200 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8098
• Wer Ortho: 0.3333
• Wer: 0.2699
• Cer: 0.1331
• Precision: 0.8395
• Recall: 0.8400
• F1: 0.8390

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: 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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer	Cer	Precision	Recall	F1
0.7695	0.2902	500	0.8098	0.3333	0.2699	0.1331	0.8395	0.8400	0.8390

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0