Gracekkk/whisper-tiny

Whisper Tiny LibriSpeech

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

• Loss: 1.0786
• Wer: 98.6153

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_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: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.0289	0.0561	100	1.0786	98.6153

Framework versions

• Transformers 5.5.3
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2