Whisper-Small-Multilingual-Uganda

This model is a fine-tuned version of openai/whisper-small on the Bateesa/popolivoice, Bateesa/buaiir_voice_jap dataset. It achieves the following results on the evaluation set:

• Loss: 0.7142
• Wer: 39.8421

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Use 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0373	11.4943	1000	0.6213	29.6482
0.0125	22.9885	2000	0.6981	37.2577
0.0008	34.4828	3000	0.6874	39.6267
0.0007	45.9770	4000	0.7142	39.8421

Framework versions

• Transformers 5.8.0
• Pytorch 2.11.0+cu130
• Datasets 2.21.0
• Tokenizers 0.22.2