LWobole/whisper-small-tl

Whisper Small Tl - LWobole

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: 0.5111
• Wer: 17.3340

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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0082	8.4746	1000	0.4410	17.2100
0.0008	16.9492	2000	0.4821	16.8456
0.0004	25.4237	3000	0.5031	17.3030
0.0003	33.8983	4000	0.5111	17.3340

Framework versions

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