Jerry02/whisper-tiny_to_indian_accent_5

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: 0.3162
• Wer: 14.9548

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: 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
0.1017	2.3310	1000	0.2688	25.7831
0.0263	4.6620	2000	0.2910	17.8313
0.0028	6.9930	3000	0.3093	14.9096
0.0012	9.3240	4000	0.3162	14.9548

Framework versions

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