whisper-small-hi-2400_500_132

This model is a fine-tuned version of saif-daoud/whisper-small-hi-2400_500_131 on the afrispeech-200 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8127
• Wer: 0.3434

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: 500
• training_steps: 1800
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.0318	0.5	900	0.8252	0.3442
0.9844	1.5	1800	0.8127	0.3434

Framework versions

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