Hugging Face's logo

octava
/
augmenting-strategy

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Indonesian
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
augmenting-strategy / README.md
octava's picture
octava
End of training
15e2f01 verified
preview code
|
raw
history blame contribute delete
1.92 kB
metadata
library_name: transformers
language:
  - id
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - octava/InaVoCript-1.6
metrics:
  - wer
model-index:
  - name: ID Optimized Whisper Small for Inspirasi
    results: []

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