navin-kumar-j/whisper-base-en-w-pcd-10-3

Whisper Base English with Phone Control Data - Navin Kumar J

This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5281
• Wer: 0.7206

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: 0.001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 10
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8941	0.9091	40	0.8163	0.7863
0.6802	1.8182	80	0.8102	0.8137
0.6058	2.7273	120	0.6069	1.0260
0.5837	3.6364	160	0.5835	0.6794
0.5208	4.5455	200	0.5281	0.7206

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1