Fine Tune Whisper on LibriSpeech

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

• eval_loss: 0.2510
• eval_wer: 8.8067
• eval_runtime: 109.0599
• eval_samples_per_second: 1.834
• eval_steps_per_second: 0.229
• epoch: 20.0
• step: 1000

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 5000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.52.0
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.21.4