ntviet/whisper-small-hre5.0

Whisper Small Hre 5.0, male voice, 400 steps, metric CER

This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset 7 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0501
• Cer Ortho: 12.8079
• Cer: 3.2432

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: 16
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer Ortho	Cer
0.088	3.3058	400	0.0501	12.8079	3.2432

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0