metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper-event
- generated_from_trainer
datasets:
- yt
metrics:
- wer
model-index:
- name: Whisper Small Indonesian
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: yt id
type: yt
metrics:
- name: Wer
type: wer
value: 53.80973996498282
Whisper Small Indonesian
This model is a fine-tuned version of openai/whisper-small on the yt id dataset. It achieves the following results on the evaluation set:
- Loss: 0.8425
- Wer: 53.8097
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-06
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9274 | 0.17 | 1000 | 0.9544 | 67.9787 |
| 0.8826 | 0.34 | 2000 | 0.8868 | 59.7432 |
| 0.8188 | 0.52 | 3000 | 0.8566 | 57.5255 |
| 0.8253 | 0.69 | 4000 | 0.8425 | 53.8097 |
| 0.8112 | 0.86 | 5000 | 0.8373 | 56.4425 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3