LWobole/whisper-small-tagalog

Whisper Small Tagalog - Bob

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

• Loss: 0.4392
• Wer: 16.6557

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: 8
• seed: 42
• optimizer: Use 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: 50
• training_steps: 1200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2302	1.6949	200	0.3983	19.2837
0.0482	3.3898	400	0.3991	18.2875
0.017	5.0847	600	0.4136	16.8805
0.0068	6.7797	800	0.4265	16.5355
0.0038	8.4746	1000	0.4357	16.6557
0.0031	10.1695	1200	0.4392	16.6557

Framework versions

• Transformers 4.51.3
• Pytorch 2.2.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.1