Jerry02/whisper-tiny_to_canadian_accent_5

Whisper tiny Canadian

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

• Loss: 0.5017
• Wer: 31.1828

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: 4
• 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
0.0042	2.0	1000	0.4769	22.4495
0.0025	4.0	2000	0.4894	23.2887
0.0032	6.0	3000	0.4979	29.0847
0.0019	8.0	4000	0.5017	31.1828

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1