Jerry02/whisper-tiny_to_indian_accent_2

Whisper tiny Indian

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

• Loss: 0.2780
• Wer: 16.7169

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: 6
• 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: 6000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1187	3.4965	1000	0.2622	13.5994
0.0884	6.9930	2000	0.2637	13.4036
0.0689	10.4895	3000	0.2694	17.2289
0.0453	13.9860	4000	0.2744	16.6265
0.0532	17.4825	5000	0.2773	16.7620
0.0665	20.9790	6000	0.2780	16.7169

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.21.0