whisper-small-yo_ng

This model was trained from scratch on the fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 2.7203
• Wer: 76.5287

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: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.027	10.0	500	2.2439	75.7976
0.0089	20.0	1000	2.3817	73.8661
0.006	30.0	1500	2.4194	73.1847
0.0057	40.0	2000	2.7203	76.5287

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1