whisper_large_v2

This model is a fine-tuned version of NgQuocThai/whisper-large-v2-phase2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6080
• Cer: 15.6054
• Wer: 26.4083

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 1000
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.0291	1.0	1056	0.6061	15.7840	26.8434
0.0289	2.0	2112	0.6080	15.6054	26.4083

Framework versions

• Transformers 4.55.4
• Pytorch 2.8.0+cu126
• Datasets 4.1.1
• Tokenizers 0.21.4