Whisper Small Isizulu-Asr-0.9-Speed

This model is a fine-tuned version of openai/whisper-small on the ISIZULU-ASR-0.9-SPEED dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.3053
• eval_wer: 58.5082
• eval_runtime: 23.1359
• eval_samples_per_second: 6.051
• eval_steps_per_second: 0.389
• step: 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: 1e-05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch_fused 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1