npallewela/whisper-large-v2-ap4

Whisper large v2 ap4 - 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: 0.6699
• Wer Ortho: 23.4140
• Wer: 22.7982

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
0.2021	0.2368	400	0.5504	23.9963	23.4249
0.2013	0.4737	800	0.5789	24.8299	24.2512
0.1897	0.7105	1200	0.5975	23.7491	23.2074
0.1673	0.9473	1600	0.5923	24.5520	24.0614
0.102	1.1841	2000	0.6699	23.4140	22.7982

Framework versions

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