GeorgePaulson/whisper-tiny_to_american_accent_4000_6

American_english_4000_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: 0.2043
• Wer: 10.9119

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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1224	0.9452	1000	0.2181	11.1877
0.1019	1.8904	2000	0.2079	10.7395
0.0609	2.8355	3000	0.2046	10.9809
0.1097	3.7807	4000	0.2043	10.9119

Framework versions

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