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: 40.08170676350431
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: 0.6718
- Wer: 40.0817
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: 12
- eval_batch_size: 6
- 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 |
|---|---|---|---|---|
| 0.8104 | 0.26 | 1000 | 0.8244 | 49.7374 |
| 0.7059 | 0.52 | 2000 | 0.7380 | 47.9671 |
| 0.7127 | 0.77 | 3000 | 0.6957 | 48.8360 |
| 0.5311 | 1.03 | 4000 | 0.6718 | 40.0817 |
| 0.47 | 1.29 | 5000 | 0.6645 | 40.4254 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3