joshtalks-whisper-small-hi-ft

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

• eval_loss: 0.3375
• eval_wer: 31.8853
• eval_runtime: 92.1706
• eval_samples_per_second: 0.542
• eval_steps_per_second: 0.271
• epoch: 4.8551
• step: 1500

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• 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
• training_steps: 4000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 2.16.0
• Tokenizers 0.22.1