Alsman68/whisper-capstone-full-dataset

capstone-whisper-final-training-data

This model is a fine-tuned version of openai/whisper-medium on the Simulated Aviation Audio For Capstone, Final Training Data dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Wer: 0.0565

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: 16
• eval_batch_size: 8
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	52.6316	1000	0.0001	0.0565
0.0	105.2632	2000	0.0000	0.0565
0.0	157.8947	3000	0.0000	0.0565
0.0	210.5263	4000	0.0000	0.0565

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1