jooemamba/whisper-fine-tuned-alb

Whisper Small SQ

This model is a fine-tuned version of openai/whisper-small on the Common Voice 24 Albanian dataset. It achieves the following results on the evaluation set:

• Loss: 0.1172
• Wer: 8.9025

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: 3e-05
• 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: linear
• lr_scheduler_warmup_steps: 300
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1051	1.6420	1000	0.1882	17.6296
0.0050	3.2841	2000	0.1172	8.9025

Framework versions

• Transformers 5.1.0
• Pytorch 2.9.0+cu126
• Datasets 4.5.0
• Tokenizers 0.22.2