Hugging Face's logo

octava
/
optimized-sm-whisper-id

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Indonesian
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
optimized-sm-whisper-id / README.md
octava's picture
octava
End of training
69ebad1 verified
preview code
|
raw
history blame contribute delete
2.65 kB
metadata
library_name: transformers
language:
  - id
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - octava/indonesian-voice-transcription-1.4.9a-cv-fl-slrjv-md
metrics:
  - wer
model-index:
  - name: Optimized Whisper Small Id for Inspirasi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Extracted Youtube with CommonVoice11, Fleurs, OpenSLR, and MagicData
          type: octava/indonesian-voice-transcription-1.4.9a-cv-fl-slrjv-md
          args: 'config: id, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 19.96201329534663

Optimized Whisper Small Id for Inspirasi

This model is a fine-tuned version of openai/whisper-small on the Extracted Youtube with CommonVoice11, Fleurs, OpenSLR, and MagicData dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3376
  • Wer: 19.9620

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: 32
  • eval_batch_size: 16
  • 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
0.4122 0.1686 500 0.3999 24.8908
0.2737 0.3373 1000 0.3655 22.4691
0.2311 0.5059 1500 0.3491 21.5195
0.1947 0.6745 2000 0.3339 21.5100
0.169 0.8432 2500 0.3408 20.6363
0.0875 1.0118 3000 0.3429 21.2726
0.0877 1.1804 3500 0.3430 20.4748
0.0726 1.3491 4000 0.3396 20.2469
0.0741 1.5177 4500 0.3378 20.2754
0.0675 1.6863 5000 0.3376 19.9620

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.2.0a0+81ea7a4
  • Datasets 3.3.2
  • Tokenizers 0.21.0