whisper-base-ClearSpeak

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

• eval_loss: 0.0543
• eval_wer: 1.9591
• eval_runtime: 149.6409
• eval_samples_per_second: 3.555
• eval_steps_per_second: 0.448
• epoch: 12.4060
• step: 1650

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: 16
• eval_batch_size: 8
• seed: 42
• 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: 100
• training_steps: 2000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 5.4.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2