octava/augmenting-strategy

ID Optimized Whisper Small for Inspirasi

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

• Loss: 0.3682
• Wer: 14.6104

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0046	5.4054	1000	0.3295	14.9351
0.0004	10.8108	2000	0.3417	14.3506
0.0002	16.2162	3000	0.3556	14.7078
0.0002	21.6216	4000	0.3643	14.6753
0.0001	27.0270	5000	0.3682	14.6104

Framework versions

• Transformers 4.51.3
• Pytorch 2.2.0a0+81ea7a4
• Datasets 3.6.0
• Tokenizers 0.21.1