octava/combined-augmentation-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: 0.3206
• Wer: 14.8052

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: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0493	1.6447	1000	0.2928	15.9091
0.0021	3.2895	2000	0.3111	14.3506
0.0008	4.9342	3000	0.3206	14.8052

Framework versions

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