metadata

library_name: transformers
language:
  - id
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - octava/extracted-id-subbed-video-v2
metrics:
  - wer
model-index:
  - name: Whisper Small Id - Inspirasi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Extracted id video v2
          type: octava/extracted-id-subbed-video-v2
          config: id
          split: test
          args: 'config: id, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 27.433834131820085

Whisper Small Id - Inspirasi

This model is a fine-tuned version of openai/whisper-small on the Extracted id video v2 dataset. It achieves the following results on the evaluation set:

Loss: 0.5409
Wer: 27.4338

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
gradient_accumulation_steps: 2
total_train_batch_size: 64
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
0.0774	2.2424	1000	0.4203	29.0804
0.0129	4.4848	2000	0.4827	28.1222
0.0035	6.7273	3000	0.5214	28.4106
0.0014	8.9697	4000	0.5278	27.3594
0.001	11.2110	5000	0.5409	27.4338

Framework versions

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