Downloads · 30 days
3
5% of all-time downloads
whispertiny_buah25sil_v1_3
albertuspekerti/whispertiny_buah25sil_v1_3
whispertiny_buah25sil_v1_3 is a machine learning model from albertuspekerti. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
65
Public
Parameters
37.8M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 25, 2026
- Updated
- Feb 25, 2026
- SHA
- 3a56ae08
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
whispertiny_buah25sil_v1_3
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0511
- Wer: 6.4685
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0193 | 0.2286 | 1000 | 0.0425 | 10.3203 |
| 0.0102 | 0.4571 | 2000 | 0.0427 | 8.2060 |
| 0.0081 | 0.6857 | 3000 | 0.0384 | 7.4733 |
| 0.0072 | 0.9143 | 4000 | 0.0402 | 7.3268 |
| 0.0039 | 1.1429 | 5000 | 0.0370 | 6.4476 |
| 0.0071 | 1.3714 | 6000 | 0.0530 | 7.7873 |
| 0.0033 | 1.6 | 7000 | 0.0531 | 7.4105 |
| 0.0055 | 1.8286 | 8000 | 0.0424 | 6.1126 |
| 0.0013 | 2.0571 | 9000 | 0.0524 | 6.9709 |
| 0.0008 | 2.2857 | 10000 | 0.0511 | 6.4685 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 4.0.0
- Tokenizers 0.19.1
- Type
- whisper
- License
- apache-2.0
- Created
- Feb 25, 2026
- Updated
- Feb 25, 2026