GeorgePaulson/whisper-tiny_to_american_accent_3000_6

American_english_3000_106

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

• Loss: 0.2299
• Wer: 12.4634

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: 2
• eval_batch_size: 1
• 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: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2075	0.9452	1000	0.2666	18.1865
0.1632	1.8904	2000	0.2357	12.6702
0.1088	2.8355	3000	0.2299	12.4634

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1