npallewela/whisper-large-v2-ap1

Whisper large v2 ap3 - Nuwan 4000

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: 0.5519
• Wer Ortho: 29.7334
• Wer: 29.0117

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
0.6232	0.2368	400	0.6759	40.8009	39.6457
0.5312	0.4737	800	0.6170	38.6556	37.7024
0.5302	0.7105	1200	0.5849	35.3744	34.4701
0.4828	0.9473	1600	0.5638	32.1974	31.4177
0.4344	1.1841	2000	0.5519	29.7334	29.0117

Framework versions

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