whisper-small-hi-2400_500_133

This model is a fine-tuned version of saif-daoud/whisper-small-hi-2400_500_132 on the afrispeech-200 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7843
• Wer: 0.3273

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-06
• train_batch_size: 8
• 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: 150
• training_steps: 540
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9568	0.5	270	0.7916	0.3298
0.9337	1.5	540	0.7843	0.3273

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.11.0
• Tokenizers 0.13.2