DeathCover1003/whisper-tiny_to_british_accent_4000_1e-5

Whisper tiny British

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

• Loss: 0.3266
• Wer: 12.5156

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: 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
0.3303	0.9901	1000	0.3050	15.4889
0.1802	1.9802	2000	0.3063	12.8890
0.0396	2.9703	3000	0.3203	12.6262
0.0082	3.9604	4000	0.3266	12.5156

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0