npallewela/whisper-large-v2-ap5

Whisper large v2 ap5 - Nuwan

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7629
• Wer Ortho: 23.2118
• Wer: 22.6459

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1438	0.2368	400	0.6077	24.1210	23.5395
0.1508	0.4737	800	0.6197	23.6388	23.1520
0.1341	0.7105	1200	0.6505	22.9400	22.4285
0.1075	0.9473	1600	0.6673	23.9861	23.4209
0.0532	1.1841	2000	0.7629	23.2118	22.6459

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1