Downloads · 30 days
6
13% of all-time downloads
whisper-small-korean-lightaug
NgQuocThai/whisper-small-korean-lightaug
whisper-small-korean-lightaug is a automatic speech recognition model from NgQuocThai. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
46
Public
Parameters
242M
4.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 31, 2025
- Updated
- Sep 2, 2025
- SHA
- 0224e75b
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. -->
whisper-small-korean-lightaug
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7346
- Cer: 26.9409
- Wer: 43.9932
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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_ratio: 0.05
- num_epochs: 11
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 2.3854 | 1.0 | 2702 | 0.8705 | 34.8852 | 58.2564 |
| 1.3708 | 2.0 | 5404 | 0.8087 | 31.6125 | 52.0342 |
| 1.1855 | 3.0 | 8106 | 0.7731 | 28.8266 | 48.4239 |
| 1.0676 | 4.0 | 10808 | 0.7648 | 29.0730 | 46.9538 |
| 0.9922 | 5.0 | 13510 | 0.7548 | 30.7859 | 49.4496 |
| 0.9279 | 6.0 | 16212 | 0.7440 | 28.5246 | 46.3795 |
| 0.8727 | 7.0 | 18914 | 0.7366 | 28.7591 | 46.4957 |
| 0.8381 | 8.0 | 21616 | 0.7346 | 26.9409 | 43.9932 |
| 0.8067 | 9.0 | 24318 | 0.7294 | 27.0224 | 44.2120 |
| 0.7889 | 10.0 | 27020 | 0.7263 | 27.1436 | 43.9521 |
| 0.7678 | 11.0 | 29722 | 0.7294 | 27.0621 | 44.0068 |
Framework versions
- Transformers 4.56.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.22.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 31, 2025
- Updated
- Sep 2, 2025