whisper-small-shona-waxal

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5100
• eval_wer: 52.0133
• eval_runtime: 157.3423
• eval_samples_per_second: 1.271
• eval_steps_per_second: 0.159
• epoch: 2.0295
• step: 4000

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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 5.13.1
• Pytorch 2.11.0+cu128
• Datasets 2.21.0
• Tokenizers 0.22.2